© 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. 12970
    Prev
    Next
    INDEX
    Explanations

    open file for write

    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
    rounds
    0.64
    ક્
    0.61
    dob
    0.59
    double
    0.58
    满
    0.55
    Elo
    0.55
    round
    0.54
    滿
    0.54
    DOUBLE
    0.54
    ritu
    0.54
    POSITIVE LOGITS
     BF
    0.72
     A
    0.70
     bf
    0.66
     Brix
    0.66
     В
    0.65
     AE
    0.62
     Bf
    0.61
     BB
    0.61
     AEW
    0.60
     harmonic
    0.60
    Activations Density 0.037%

    No Known Activations