© 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. 20
    Prev
    Next
    INDEX
    Explanations

    is arguably the

    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
    =\$
    0.98
    佸
    0.95
    runken
    0.91
     нуля
    0.91
    เพื่อ
    0.88
    โทษ
    0.87
    目的是
    0.87
     *}(
    0.85
     क्रमश
    0.85
    ලු
    0.85
    POSITIVE LOGITS
     one
    4.18
    one
    3.19
     één
    3.12
     salah
    3.11
     одной
    3.11
     одного
    3.04
     واحدة
    3.01
     одном
    2.99
     ONE
    2.94
     один
    2.93
    Activations Density 4.843%

    No Known Activations