© 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. 106451
    Prev
    Next
    INDEX
    Explanations

    horror movie titles

    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
    iotti
    -0.86
    quotation
    -0.73
    magical
    -0.72
     sfer
    -0.72
     клетки
    -0.72
     الخاص
    -0.71
    GCD
    -0.71
    alne
    -0.70
     quotation
    -0.70
     noqa
    -0.69
    POSITIVE LOGITS
     ghost
    1.28
     spirits
    1.24
     ghosts
    1.22
    ghost
    1.20
    贞
    1.04
     Geister
    1.01
     horror
    0.99
    entities
    0.95
    Ghost
    0.95
     Ghost
    0.91
    Activations Density 0.015%

    No Known Activations