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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 423
    Prev
    Next
    INDEX
    Explanations

    }</

    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
     bed
    1.34
     quasi
    1.34
     for
    1.32
     in
    1.30
     ,
    1.29
    ,
    1.28
     fell
    1.28
     .*
    1.27
     ran
    1.27
     on
    1.26
    POSITIVE LOGITS
    isasi
    1.76
    typeparam
    1.73
    Hochspringen
    1.68
    jumlah
    1.64
     pesquis
    1.64
    NameValuePair
    1.63
     jornalista
    1.62
     filóso
    1.62
    WarningLevel
    1.61
    िस्थित
    1.60
    Activations Density 0.017%

    No Known Activations