© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-270M
    3. 15-GEMMASCOPE-2-RES-16K
    4. 4014
    Prev
    Next
    INDEX
    Explanations

    format: Question: SQLQuery: Schema Description:

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_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
    @
    1.73
    [
    1.68
     button
    1.68
     +
    1.67
     Past
    1.65
     paper
    1.64
    ï
    1.63
    <strong>
    1.63
    liner
    1.63
     @
    1.62
    POSITIVE LOGITS
     hổ
    1.24
    ыргыз
    1.13
    侑
    1.08
     zav
    1.06
    امن
    1.02
    สต
    1.00
     acel
    0.99
     odre
    0.99
    ังส
    0.99
     prostor
    0.98
    Activations Density 0.006%

    No Known Activations