© 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. 30930
    Prev
    Next
    INDEX
    Explanations

    refer to

    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
     Maximilian
    -0.81
     caribe
    -0.81
     Sheng
    -0.73
    detail
    -0.72
     confirmación
    -0.70
     Église
    -0.69
    Known
    -0.69
     Ona
    -0.69
    ്‍
    -0.68
    ITUTE
    -0.68
    POSITIVE LOGITS
    cambrian
    0.84
    ECONDS
    0.75
     Commerce
    0.74
     pięk
    0.71
    完成后
    0.71
    ieh
    0.70
    Hamster
    0.69
    Disposal
    0.68
    優勝
    0.68
    cec
    0.68
    Activations Density 0.017%

    No Known Activations