© 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. 93484
    Prev
    Next
    INDEX
    Explanations

    San Javier

    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
    schuh
    -0.83
     vô
    -0.83
    同学们
    -0.82
     Hough
    -0.77
     spacers
    -0.77
    ifikationen
    -0.76
    GROSS
    -0.76
    lief
    -0.75
    オリティ
    -0.75
     ilyen
    -0.74
    POSITIVE LOGITS
    beast
    0.85
    reds
    0.84
     Twice
    0.79
     twice
    0.78
     mixtures
    0.76
    利益
    0.75
     conseguido
    0.75
     boat
    0.75
    ıyla
    0.74
    ♃
    0.74
    Activations Density 0.031%

    No Known Activations