© 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. 116230
    Prev
    Next
    INDEX
    Explanations

    packing paths / file paths

    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
    Frauen
    -0.82
     anonymously
    -0.79
    Große
    -0.78
    Шо
    -0.76
    Celular
    -0.75
     episcopal
    -0.75
    Foreground
    -0.74
     ניתן
    -0.74
     miệng
    -0.73
    Новые
    -0.73
    POSITIVE LOGITS
     тран
    0.92
    ތ
    0.83
     Col
    0.82
     sentimentos
    0.79
    BLK
    0.79
    owing
    0.78
     Colonel
    0.76
    tile
    0.76
    jiang
    0.75
    }^{(
    0.74
    Activations Density 0.025%

    No Known Activations