© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108708
    Prev
    Next
    INDEX
    Explanations

    data visualization plotting statistics

    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
     banding
    -0.82
     tolerant
    -0.80
    argout
    -0.79
    >),
    -0.78
    摇
    -0.75
    żli
    -0.74
    ̃o
    -0.73
    liculas
    -0.70
     priority
    -0.69
     Dodd
    -0.68
    POSITIVE LOGITS
    lanatory
    0.85
     Fath
    0.84
     Augsburg
    0.82
    IQR
    0.78
     explanatory
    0.78
     lurking
    0.77
     抽
    0.77
    explanatory
    0.76
     ekolog
    0.73
     статисти
    0.73
    Activations Density 0.046%

    No Known Activations