© 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-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 64998
    Prev
    Next
    INDEX
    Explanations

    pixel values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     軽量
    -1.03
    vVar
    -0.95
     entrare
    -0.93
    itae
    -0.92
     però
    -0.92
     botão
    -0.91
    nev
    -0.91
    ctors
    -0.91
    ‘‘
    -0.91
     где
    -0.90
    POSITIVE LOGITS
    ruta
    0.95
    Lj
    0.91
     използ
    0.90
     diphtheria
    0.87
    Посилання
    0.87
    与此同时
    0.84
    estación
    0.84
    ريط
    0.83
    先は
    0.81
     Oficial
    0.81
    Activations Density 0.003%

    No Known Activations