© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 48698
    Prev
    Next
    INDEX
    Explanations

    news and events

    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
     of
    -1.63
     somewhat
    -1.07
     sufficiently
    -1.01
     piece
    -1.00
    onym
    -0.94
    ่าง
    -0.94
     хоть
    -0.90
    hibe
    -0.90
     imparts
    -0.90
     qualcosa
    -0.89
    POSITIVE LOGITS
     firepower
    1.17
     stuff
    1.13
     and
    1.13
     than
    1.01
     compared
    0.99
     juice
    0.97
     разнообраз
    0.96
     špat
    0.95
    stuff
    0.93
     variability
    0.92
    Activations Density 0.112%

    No Known Activations