© 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. 3505
    Prev
    Next
    INDEX
    Explanations

    install packages

    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
    disposing
    2.45
     syllables
    2.41
     Анали
    2.40
     tablecloth
    2.32
    ⁸
    2.32
    ква
    2.32
    ぞれ
    2.31
    Seriously
    2.31
    ⁹
    2.31
    ReferencePose
    2.30
    POSITIVE LOGITS
    as
    3.48
    s
    3.35
    ing
    3.27
    in
    3.13
    akarta
    2.86
    ي
    2.78
    ar
    2.75
    at
    2.74
    ী
    2.73
    sman
    2.61
    Activations Density 0.001%

    No Known Activations