© 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. 94221
    Prev
    Next
    INDEX
    Explanations

    items, contact, functions, agents

    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
    Continuing
    -1.04
    oneof
    -1.02
     empaque
    -1.01
    baly
    -0.99
     lámparas
    -0.97
    "$
    -0.96
    izze
    -0.95
    lent
    -0.94
    lease
    -0.94
     lixo
    -0.94
    POSITIVE LOGITS
     this
    1.07
     with
    1.02
     relatively
    1.00
     also
    0.95
     sultry
    0.93
     solidly
    0.92
     can
    0.91
    ństwa
    0.91
    ﻜ
    0.90
     veritable
    0.89
    Activations Density 0.001%

    No Known Activations