© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 13748
    Prev
    Next
    INDEX
    Explanations

    classified island

    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_13_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
     Société
    1.47
     LaSalle
    1.30
     Elsewhere
    1.30
     Societe
    1.30
    Murphy
    1.28
    ");
    1.27
    oodoo
    1.27
     ấy
    1.27
    ');
    1.26
     physicist
    1.26
    POSITIVE LOGITS
    rota
    1.12
    i
    1.08
    ral
    1.06
    ion
    0.98
    reth
    0.98
    ional
    0.97
    centes
    0.95
     perg
    0.93
    bent
    0.93
    reb
    0.92
    Activations Density 0.001%

    No Known Activations