© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 240994
    Prev
    Next
    INDEX
    Explanations

    yellow gold necklace

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    Christine
    0.46
    getStudentNo
    0.40
     auctioned
    0.40
    찬가지
    0.40
     parceria
    0.39
    [,,"
    0.39
    DanhMuc
    0.39
    𝚢
    0.38
    აბ
    0.37
    рию
    0.37
    POSITIVE LOGITS
     It
    0.51
     வலி
    0.44
     ಸಂಪ
    0.42
     V
    0.42
     ಆತ್ಮ
    0.40
    锗
    0.40
     acceleration
    0.40
     long
    0.39
     Lesser
    0.39
     longer
    0.39
    Activations Density 0.000%

    No Known Activations