© 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. 190364
    Prev
    Next
    INDEX
    Explanations

    administrators platform inquiries analytics studies

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

    precursor to computing or llama

    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
    ̀i
    0.52
     ér
    0.48
    िए
    0.45
    ոն
    0.44
    ﯽ
    0.43
    _{
    0.42
     U
    0.42
    他的
    0.42
    ﻰ
    0.41
     ratification
    0.41
    POSITIVE LOGITS
    க
    0.49
    sr
    0.49
     Nails
    0.48
     Enseñ
    0.47
     intensively
    0.47
    late
    0.46
    pint
    0.46
    larınız
    0.46
    aliers
    0.45
    avali
    0.45
    Activations Density 0.001%

    No Known Activations