© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 47458
    Prev
    Next
    INDEX
    Explanations

    service or permit

    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
     infile
    -0.80
     Flüs
    -0.75
    pleasant
    -0.75
    寥
    -0.73
     killed
    -0.73
     løs
    -0.72
     Wales
    -0.71
     Malta
    -0.70
    midler
    -0.69
     pleasant
    -0.69
    POSITIVE LOGITS
    ߯
    0.85
    нциклопе
    0.85
    ────
    0.82
     senador
    0.81
     می‌
    0.81
     декора
    0.81
     metropolitana
    0.80
    铵
    0.79
    ̲
    0.79
    ุป
    0.78
    Activations Density 0.048%

    No Known Activations