© 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. 137139
    Prev
    Next
    INDEX
    Explanations

    business objectives and services

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

    docker type definitions

    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
     carr
    0.54
     in
    0.53
    f
    0.53
    ers
    0.52
    handlers
    0.48
    ta
    0.48
    P
    0.47
     alleg
    0.46
    find
    0.45
     Nek
    0.45
    POSITIVE LOGITS
    ння
    0.50
    їв
    0.49
    примеча
    0.49
    Ꮘ
    0.49
    イヤ
    0.48
    詠
    0.48
    эф
    0.48
    EFFECT
    0.48
    дования
    0.48
    вален
    0.48
    Activations Density 0.004%

    No Known Activations