© 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. 17-GEMMASCOPE-2-RES-16K
    7. 1872
    Prev
    Next
    INDEX
    Explanations

    bank accounts and statements

    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_17_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
     who
    1.25
    who
    1.14
     whom
    1.02
    concentration
    1.00
     profondément
    0.99
     système
    0.99
     profesión
    0.99
    煩
    0.97
    ὥ
    0.97
     самостоя
    0.97
    POSITIVE LOGITS
     spokesman
    1.45
     founder
    1.44
     spokeswoman
    1.43
     Başkanı
    1.38
     lawmaker
    1.35
    创始人
    1.35
     leader
    1.34
     officials
    1.33
     representatives
    1.29
     Chairman
    1.27
    Activations Density 0.386%

    No Known Activations