© 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. 13-GEMMASCOPE-2-RES-16K
    7. 2548
    Prev
    Next
    INDEX
    Explanations

    chemical elements listed

    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_13_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
    <start_of_image>
    1.23
    ...
    1.01
    ↵
    0.92
    <0xC2>
    0.90
    0.87
    ↵↵
    0.86
    no
    0.82
    ano
    0.82
    <em>
    0.81
    ^
    0.78
    POSITIVE LOGITS
    ꗤ
    2.10
    <unused353>
    2.06
    <unused167>
    2.02
    <unused1831>
    2.02
    <unused130>
    1.99
    <unused1893>
    1.99
    <unused1208>
    1.98
    <unused1735>
    1.98
    <unused1954>
    1.95
     NPTypeCode
    1.95
    Activations Density 1.950%

    No Known Activations