© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13794
    Prev
    Next
    INDEX
    Explanations

    `(` followed by date

    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
    Negative Logits
     ≤
    0.64
     dominates
    0.63
     oscillators
    0.63
     distributions
    0.62
     DataLoader
    0.62
     SUVs
    0.61
     calculators
    0.61
     ($\
    0.59
     dalamnya
    0.59
    ≤
    0.59
    POSITIVE LOGITS
    toast
    0.62
    stmt
    0.58
    hash
    0.53
    ,"%
    0.53
    রি
    0.52
    Vie
    0.52
    üml
    0.52
    eval
    0.51
    prompt
    0.51
    greeting
    0.51
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.