© 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. 11409
    Prev
    Next
    INDEX
    Explanations

    thank you for

    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
    Bec
    2.81
    Asimismo
    2.33
    엿
    2.31
    어서
    2.25
    emap
    2.23
    LLI
    2.21
    G
    2.19
    TLE
    2.17
     заклад
    2.14
    是对
    2.12
    POSITIVE LOGITS
    дже
    4.02
    น
    3.22
    л
    3.13
    ल
    3.12
    re
    3.02
    rza
    3.02
    uosa
    3.00
    कम
    2.97
    起こ
    2.92
    ла
    2.90
    Activations Density 0.010%

    No Known Activations