© 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. 14518
    Prev
    Next
    INDEX
    Explanations

    Earth

    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
    ‍♀️
    2.81
    ഷേധ
    2.77
    ‍♂️
    2.75
    essive
    2.43
    adino
    2.42
    arini
    2.41
    oconvex
    2.38
    quez
    2.28
    aien
    2.26
     pictureBox
    2.24
    POSITIVE LOGITS
    汅
    2.60
    chent
    2.45
    getitem
    2.39
    chen
    2.38
    ا
    2.38
    क्षित
    2.29
     sareng
    2.29
    ূর্ন
    2.25
    Compilation
    2.24
    Geography
    2.24
    Activations Density 0.010%

    No Known Activations