© 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. 7-GEMMASCOPE-2-RES-16K
    7. 3542
    Prev
    Next
    INDEX
    Explanations

    scientific terms

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ized
    1.26
    ization
    1.21
    -
    1.19
     end
    1.18
    ly
    1.13
    ness
    1.10
    age
    1.07
     strike
    1.04
    izing
    1.03
    ry
    1.02
    POSITIVE LOGITS
    <unused1481>
    1.86
    婫
    1.85
    仹
    1.85
     benefícios
    1.85
    Não
    1.83
     pédicule
    1.83
    <unused1287>
    1.83
    <unused1352>
    1.82
    少し
    1.81
     duże
    1.80
    Activations Density 0.151%

    No Known Activations