© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 56686
    Prev
    Next
    INDEX
    Explanations

    passer, passing, Passyunk, Pasing

    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
    Negative Logits
     Incidents
    -0.92
     Advance
    -0.85
    exemplar
    -0.84
     tutu
    -0.81
     depra
    -0.80
     Adapt
    -0.80
    plateau
    -0.80
    Dimens
    -0.79
    Exposition
    -0.78
     själv
    -0.77
    POSITIVE LOGITS
    by
    0.81
    BY
    0.81
    bys
    0.78
    SV
    0.77
    CM
    0.75
    SB
    0.75
     wakati
    0.75
    Hamilton
    0.73
    AK
    0.72
    PS
    0.71
    Activations Density 0.046%

    No Known Activations