© 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. 22-GEMMASCOPE-2-RES-16K
    7. 10524
    Prev
    Next
    INDEX
    Explanations

    listen without judgment

    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_22_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
     ખાતે
    0.93
     صغير
    0.77
    __);
    0.75
     förs
    0.73
    HHHH
    0.72
    ).—
    0.71
     الاكس
    0.71
    ₎
    0.70
    MEX
    0.69
     swe
    0.69
    POSITIVE LOGITS
    trust
    0.84
    용한
    0.83
    anggung
    0.77
    仇
    0.76
    umpang
    0.76
    untut
    0.76
    atap
    0.76
    看过
    0.75
    смотре
    0.75
    unjuk
    0.75
    Activations Density 0.032%

    No Known Activations