© 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. 110688
    Prev
    Next
    INDEX
    Explanations

    needed for, other artisans, after the

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

    generate text

    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
    ↵↵↵↵↵
    0.45
    subscriptions
    0.44
    餐厅
    0.43
    érios
    0.42
     مخالف
    0.42
    ņas
    0.42
    kn
    0.41
    zo
    0.41
     روز
    0.41
    deletion
    0.41
    POSITIVE LOGITS
     permintaan
    0.49
     chad
    0.48
     ori
    0.46
    .,"
    0.46
    휙
    0.46
    ."-
    0.46
     minta
    0.46
     adiab
    0.46
     ryzy
    0.46
    ాలి
    0.46
    Activations Density 0.000%

    No Known Activations