© 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. 485
    Prev
    Next
    INDEX
    Explanations

    don't

    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
    𝐒
    0.98
     viên
    0.91
     sehari
    0.91
    推理
    0.86
    क्षणिक
    0.86
    jskiego
    0.84
    笳
    0.84
     berbasis
    0.84
    കാശ
    0.83
    ><%=
    0.83
    POSITIVE LOGITS
    ât
    1.04
    ít
    0.96
    comstockfootage
    0.93
    稚
    0.91
    '
    0.90
    keys
    0.86
    <unused180>
    0.84
    ’
    0.82
    檛
    0.79
    <0x82>
    0.79
    Activations Density 0.759%

    No Known Activations