© 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. 23772
    Prev
    Next
    INDEX
    Explanations

    by or with context

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

    geared towards reviews and research

    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
     главное
    0.46
     это
    0.45
     egyéb
    0.45
    甪
    0.45
    zieć
    0.44
     milyen
    0.44
     用
    0.44
     vendre
    0.43
     cocinar
    0.42
     这是
    0.42
    POSITIVE LOGITS
    mod
    0.48
    new
    0.45
    steam
    0.42
    mael
    0.42
    モ
    0.42
    lepas
    0.41
    moda
    0.41
    submarine
    0.40
    supabase
    0.40
     احمد
    0.40
    Activations Density 0.001%

    No Known Activations