© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 58864
    Prev
    Next
    INDEX
    Explanations

    documentation files

    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_34/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
    擘
    -0.79
     Aula
    -0.77
    🏇
    -0.75
    omás
    -0.74
     dourada
    -0.73
     Ego
    -0.73
    tických
    -0.73
    義務
    -0.71
     liberalism
    -0.70
    gól
    -0.69
    POSITIVE LOGITS
     Nevada
    0.92
     SUN
    0.84
    žuje
    0.81
    ффек
    0.79
    мое
    0.78
    fordshire
    0.77
     осве
    0.75
    header
    0.74
    guma
    0.74
    ূ
    0.73
    Activations Density 0.019%

    No Known Activations