© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 893
    Prev
    Next
    INDEX
    Explanations

    index and names

    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
     city
    0.94
     urban
    0.87
     institutional
    0.87
     ​​
    0.85
     es
    0.83
     rele
    0.82
     industrialized
    0.81
     governmental
    0.80
     public
    0.78
     be
    0.77
    POSITIVE LOGITS
    ColumnKind
    1.55
    fnamefont
    1.41
    াতাড়ি
    1.41
    <unused1463>
    1.41
    >)`](
    1.39
    逘
    1.38
    গুলির
    1.38
    संख्या
    1.37
    টির
    1.37
    TypeText
    1.37
    Activations Density 0.525%

    No Known Activations