© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 3705
    Prev
    Next
    INDEX
    Explanations

    moves on its own

    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
    kor
    1.47
    port
    1.45
    production
    1.45
    ters
    1.45
    ｡
    1.44
    selen
    1.44
    쇼
    1.43
    ։
    1.42
     জোট
    1.42
    クロ
    1.42
    POSITIVE LOGITS
     "?"]
    2.01
    ยนต์
    1.93
    %",
    1.87
     *"
    1.79
    علم
    1.76
    ificant
    1.73
     Throwable
    1.72
    atical
    1.72
    %"
    1.71
    hensible
    1.70
    Activations Density 0.000%

    No Known Activations