© 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. 407
    Prev
    Next
    INDEX
    Explanations

    more information or options

    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
    s
    1.06
    ساب
    1.06
    getTable
    0.92
    ⓤ
    0.90
    uições
    0.88
    スマ
    0.86
    এটি
    0.86
    तीय
    0.85
    F
    0.85
    vođa
    0.85
    POSITIVE LOGITS
    than
    1.08
     afield
    0.95
    لين
    0.94
     than
    0.94
    ಣೆ
    0.87
    ल
    0.85
    THAN
    0.85
    ტის
    0.84
    لین
    0.81
    llo
    0.81
    Activations Density 1.877%

    No Known Activations