© 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. 10009
    Prev
    Next
    INDEX
    Explanations

    youtube web addresses

    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
    1.16
     autop
    1.06
    קות
    1.03
     than
    1.01
    0.98
    than
    0.98
    ૯
    0.98
    0.98
    0.97
    0.97
    POSITIVE LOGITS
    揉
    0.95
     Ibid
    0.91
     jár
    0.87
    我也是
    0.83
    解除
    0.82
    瞒
    0.82
     Anche
    0.81
    琭
    0.81
    Ibid
    0.80
     heals
    0.79
    Activations Density 0.009%

    No Known Activations