© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 4182
    Prev
    Next
    INDEX
    Explanations

    game combat discussions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_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
    Roses
    1.82
    larghezza
    1.81
    Poems
    1.80
    Thrown
    1.79
    Storia
    1.79
    Musical
    1.78
    Arquivo
    1.74
    Maggie
    1.70
    <unused1487>
    1.69
    Databaze
    1.68
    POSITIVE LOGITS
     versus
    1.63
     and
    1.60
     challenges
    1.47
    s
    1.38
    ‐
    1.38
     complement
    1.32
     via
    1.31
    ,
    1.31
     Vad
    1.30
     challenge
    1.29
    Activations Density 0.104%

    No Known Activations