© 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. 115035
    Prev
    Next
    INDEX
    Explanations

    long-term effects

    np_acts-logits-general · gemini-2.5-flash-lite

    complex descriptive terms

    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
    т
    0.59
    ID
    0.54
    옥
    0.54
    mar
    0.53
    the
    0.50
    We
    0.50
    י
    0.49
    Developers
    0.49
    ശ്ശ
    0.48
    ()];
    0.48
    POSITIVE LOGITS
     لج
    0.48
     الشعر
    0.45
     قواعد
    0.45
     ক্রি
    0.45
     Shifts
    0.44
     Psalm
    0.44
     Univ
    0.44
     perust
    0.44
     শীতল
    0.43
     Polyn
    0.43
    Activations Density 0.001%

    No Known Activations