© 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. 47386
    Prev
    Next
    INDEX
    Explanations

    ст... + syllable

    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
     ${(
    -0.91
     billet
    -0.87
    fört
    -0.84
     pelican
    -0.82
     Himal
    -0.82
     plums
    -0.80
    vangen
    -0.80
     Myco
    -0.79
    తో
    -0.79
    nemen
    -0.79
    POSITIVE LOGITS
    ところに
    1.04
     old
    0.92
    GREES
    0.86
    場所に
    0.86
     rocas
    0.84
     column
    0.81
     belt
    0.79
     convertirse
    0.79
     crowded
    0.78
     conoci
    0.78
    Activations Density 0.004%

    No Known Activations