© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 23553
    Prev
    Next
    INDEX
    Explanations

    birth, pregnancy, facts, rights

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

    config, plan, options, details, evolving

    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
    t
    0.68
    I
    0.66
    ;
    0.61
    U
    0.60
    ↵
    0.58
    V
    0.57
    D
    0.57
    Layout
    0.54
     I
    0.54
    in
    0.54
    POSITIVE LOGITS
     सुनने
    0.55
    觧
    0.55
     conhecimentos
    0.52
    數學
    0.52
    𒊺
    0.51
     моих
    0.50
    но
    0.49
     музыки
    0.49
     conocimientos
    0.48
    鲇
    0.48
    Activations Density 0.000%

    No Known Activations