© 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. 219206
    Prev
    Next
    INDEX
    Explanations

    costs, repair, default, values, depth

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

    evaluating large performance

    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
    譜
    0.52
    質
    0.49
    Prevention
    0.47
    IPA
    0.47
    最初の
    0.46
    PSG
    0.46
    椛
    0.46
    SOA
    0.45
     чого
    0.44
    最初
    0.44
    POSITIVE LOGITS
     rychle
    0.49
    莺
    0.49
     Nombre
    0.48
     justicia
    0.48
     Herce
    0.47
     单
    0.46
     Ngọc
    0.46
     让
    0.46
     namen
    0.46
     带
    0.46
    Activations Density 0.001%

    No Known Activations