© 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. 64286
    Prev
    Next
    INDEX
    Explanations

    Yi Sha, The Gospel, Gobbi

    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
     boolean
    -1.02
    boolean
    -0.99
    eqnarray
    -0.89
     двумя
    -0.83
    BOOLEAN
    -0.82
    AtIndexPath
    -0.81
    .~(\
    -0.81
    WireFormatLite
    -0.80
     varias
    -0.73
     године
    -0.73
    POSITIVE LOGITS
    [,]
    0.89
    guerra
    0.83
    仡
    0.80
     pinion
    0.79
    oca
    0.79
     להשת
    0.79
     FEW
    0.78
     сказать
    0.78
    Marked
    0.77
     角色
    0.75
    Activations Density 0.000%

    No Known Activations