© 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. 7-GEMMASCOPE-2-RES-16K
    7. 14065
    Prev
    Next
    INDEX
    Explanations

    scientific, technical, and measurements

    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_7_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
     bloody
    2.11
     ludicrous
    1.99
    в
    1.95
     flash
    1.94
    fl
    1.93
     much
    1.89
     object
    1.87
    ↵↵
    1.85
     limit
    1.84
     insult
    1.83
    POSITIVE LOGITS
    彠
    2.46
     hijos
    2.45
     Lobkovic
    2.44
    assertArg
    2.39
     Polskiej
    2.37
     filhos
    2.35
    बाईल
    2.35
     smlou
    2.34
    我也是
    2.30
     perjanjian
    2.29
    Activations Density 0.000%

    No Known Activations