© 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. 3394
    Prev
    Next
    INDEX
    Explanations

    describing existing items and what follows

    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
     всички
    -1.16
     дуже
    -1.09
     различни
    -1.08
     jugando
    -1.07
    websocket
    -1.00
     révélé
    -0.98
     three
    -0.97
     velmi
    -0.97
     kdo
    -0.96
     цвят
    -0.96
    POSITIVE LOGITS
    .+
    1.05
     протяжении
    0.93
    ühm
    0.92
    ордина
    0.88
     Амери
    0.88
     banal
    0.88
     транспорти
    0.86
    ________________
    0.85
     prochaines
    0.85
    ，，
    0.84
    Activations Density 0.006%

    No Known Activations