© 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. 64504
    Prev
    Next
    INDEX
    Explanations

    rankings and superlatives

    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
     lebih
    -1.16
     более
    -1.00
     rất
    -0.92
     которые
    -0.84
     очень
    -0.79
    松山
    -0.78
     velmi
    -0.77
     aún
    -0.77
     ļoti
    -0.76
     更
    -0.75
    POSITIVE LOGITS
     second
    4.03
     third
    3.86
     fourth
    3.14
     fifth
    3.00
    second
    2.72
     sixth
    2.69
    third
    2.64
     seventh
    2.36
     THIRD
    2.27
    fourth
    2.23
    Activations Density 0.077%

    No Known Activations