© 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. 78560
    Prev
    Next
    INDEX
    Explanations

    Wisconsin, Wisdom, Wisp

    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
     lập
    -0.80
     Voss
    -0.74
    Vin
    -0.74
     custos
    -0.71
     europé
    -0.70
     Vin
    -0.69
    بيض
    -0.68
    vrons
    -0.68
     Abfall
    -0.68
     Belanda
    -0.68
    POSITIVE LOGITS
     Wis
    1.29
    Wis
    1.21
     wis
    1.00
     WIS
    0.84
    wis
    0.82
     entweder
    0.81
    Çok
    0.78
     محت
    0.76
    DataSetChanged
    0.73
    pedia
    0.73
    Activations Density 0.019%

    No Known Activations