© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 12960
    Prev
    Next
    INDEX
    Explanations

    scan for information

    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
     Ху
    1.52
    Х
    1.46
    nect
    1.43
    YX
    1.42
     ха
    1.40
    Т
    1.40
    ostrum
    1.40
     وب
    1.40
     Т
    1.40
    HEAD
    1.38
    POSITIVE LOGITS
    दृश्य
    1.51
    ActivityResult
    1.37
    designed
    1.35
     disusun
    1.31
     diadakan
    1.27
    mdash
    1.24
     해석
    1.23
     ziren
    1.22
    사각형
    1.20
    ৪০
    1.20
    Activations Density 0.119%

    No Known Activations