© 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. 637
    Prev
    Next
    INDEX
    Explanations

    about or concerning rules and opinions

    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
    ΰ
    1.06
    消耗
    1.05
     zvol
    1.01
    ርስ
    0.95
     గుర్
    0.93
    λού
    0.92
    匀
    0.91
     모습
    0.90
    勻
    0.88
    닙
    0.87
    POSITIVE LOGITS
     about
    2.18
     regarding
    2.11
     concerning
    1.99
    about
    1.93
    regarding
    1.89
     ABOUT
    1.86
     tentang
    1.84
     về
    1.83
     Concerning
    1.76
     pertaining
    1.73
    Activations Density 2.624%

    No Known Activations