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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 1965
    Prev
    Next
    INDEX
    Explanations

    you can

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     `${
    0.70
    "@
    0.69
     매
    0.62
    ={`${
    0.61
    (`${
    0.61
    傛
    0.60
     nargs
    0.59
     `@
    0.59
     tooling
    0.57
    Ꮿ
    0.56
    POSITIVE LOGITS
    rel
    0.65
    rings
    0.59
    rys
    0.55
    ron
    0.55
    REL
    0.55
    rels
    0.54
    itone
    0.54
    itely
    0.53
    manufacturing
    0.52
     Rel
    0.52
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.