© 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. 121230
    Prev
    Next
    INDEX
    Explanations

    utility can restore

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

    limited cooperation, shooting bullets, vast internal

    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
    িন
    0.52
    lüğ
    0.46
     Бүген
    0.45
    獺
    0.42
     इंटे
    0.42
     Conversations
    0.41
     بہانہ
    0.41
     düş
    0.40
     grosse
    0.40
     দশকের
    0.40
    POSITIVE LOGITS
    一共
    0.49
    a
    0.49
    AJ
    0.47
    １
    0.46
     photographic
    0.46
    Mgr
    0.45
     Postage
    0.45
    <0x80>
    0.45
    G
    0.43
     obil
    0.43
    Activations Density 0.000%

    No Known Activations