© 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. 204171
    Prev
    Next
    INDEX
    Explanations

    minimum ready, least begin, tour guide

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

    starts, commits, param

    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
     בה
    0.50
     وغ
    0.49
     风
    0.48
     والغ
    0.48
    hmad
    0.47
    dua
    0.47
    铠
    0.47
    isRunning
    0.47
     og
    0.46
    ricia
    0.46
    POSITIVE LOGITS
    "_
    0.49
    Projeto
    0.42
     Projeto
    0.42
    सदीय
    0.41
    फेल
    0.41
    нкт
    0.40
    約
    0.40
    약
    0.40
     "__
    0.39
    බ්
    0.39
    Activations Density 0.000%

    No Known Activations