© 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. 2785
    Prev
    Next
    INDEX
    Explanations

    standard or pdf

    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
    낍
    2.39
    낄
    2.34
    /////////
    2.31
    ächen
    2.26
    //////////
    2.24
    êts
    2.19
    тьми
    2.13
     மத்தியில்
    2.11
     footh
    2.10
     யு
    2.10
    POSITIVE LOGITS
    <bos>
    2.16
    ر
    2.05
    sine
    1.99
     carrier
    1.83
    atron
    1.82
     enf
    1.77
     plaque
    1.76
     conversion
    1.75
     derivation
    1.75
     painting
    1.74
    Activations Density 0.491%

    No Known Activations