© 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. 247
    Prev
    Next
    INDEX
    Explanations

    The neuron fires strongly on specialized technical or mechanical terms—proper nouns and domain‐specific jargon like “engine,” “oil,” “readings,” “key,” “Switch,” or “Assist Mode.”

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

    words related to physical actions, movements, or body parts in instructional or procedural contexts.

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

    second-person direct address, especially instructional or advisory language referring to the reader’s actions, body, or possessions.

    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
    咗
    0.36
     Chỉ
    0.35
    Phenyl
    0.34
    Concerning
    0.33
    لاش
    0.33
    Bool
    0.32
    Trong
    0.32
    続く
    0.32
    Không
    0.32
    isTouching
    0.31
    POSITIVE LOGITS
     into
    1.23
     onto
    0.95
     away
    0.79
    into
    0.76
     out
    0.70
     vào
    0.70
     INTO
    0.68
     down
    0.68
     Into
    0.67
     up
    0.66
    Activations Density 2.437%

    No Known Activations