© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 10873
    Prev
    Next
    INDEX
    Explanations

    override/overwrite

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires on technical/programming jargon and instruction‐style terms (e.g. “implementation,” “initialize,” “accessing,” “preferences”), i.e. code-related documentation language.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    comments or explanatory text in programming or technical documentation.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    descriptions of visceral physical or emotional reactions in the body.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    穂
    0.56
     aloof
    0.54
     कच्च
    0.52
    QueueMutex
    0.51
    winding
    0.49
    VERS
    0.49
     शै
    0.49
     berakhir
    0.49
    \!\
    0.48
     réduite
    0.48
    POSITIVE LOGITS
    Override
    1.87
     override
    1.87
    override
    1.86
     Override
    1.70
     overrides
    1.59
     overridden
    1.59
     overriding
    1.52
    Overrides
    1.23
    overwrite
    1.08
     overwrite
    1.06
    Activations Density 0.022%

    No Known Activations