© 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. 30270
    Prev
    Next
    INDEX
    Explanations

    auto increment or auto generate

    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
     buffer
    -0.76
    View
    -0.74
     view
    -0.74
     kui
    -0.74
     may
    -0.73
     pérdidas
    -0.72
    ダル
    -0.71
     align
    -0.70
     permitido
    -0.70
     estudio
    -0.69
    POSITIVE LOGITS
     concernés
    0.75
     stwor
    0.75
     PLATE
    0.74
     octaves
    0.74
    Созда
    0.72
     Amplifier
    0.71
    floxacin
    0.71
    therm
    0.70
     plex
    0.70
     recru
    0.70
    Activations Density 0.005%

    No Known Activations