© 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. 24-GEMMASCOPE-2-RES-16K
    7. 14219
    Prev
    Next
    INDEX
    Explanations

    different, specific, incompatible

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

    The neuron fires on technical performance and hardware‐specification terms—words that describe changes, requirements, or features in a technical context.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_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
     社会
    0.85
    
    0.84
     願い
    0.82
     società
    0.81
     errichtet
    0.80
     すご
    0.80
     финанси
    0.79
     демокра
    0.79
     うん
    0.79
     institución
    0.79
    POSITIVE LOGITS
    0.90
    /
    0.86
     phenolic
    0.80
     unsuitable
    0.78
     ingredients
    0.78
     specific
    0.77
     products
    0.76
     T
    0.75
     C
    0.75
     K
    0.73
    Activations Density 0.007%

    No Known Activations