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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 54143
    Prev
    Next
    INDEX
    Explanations

    numbers and specific names

    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_22/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
     what
    -1.11
    Some
    -1.06
    haviours
    -1.00
     some
    -0.99
     prak
    -0.98
     Some
    -0.97
     объекта
    -0.95
    сол
    -0.93
    what
    -0.93
     prosi
    -0.93
    POSITIVE LOGITS
    所以在
    1.04
    Gilla
    1.03
     sooo
    0.95
    があるので
    0.94
    ethene
    0.91
     centroid
    0.91
     ofc
    0.90
     acesta
    0.89
     again
    0.88
     queste
    0.88
    Activations Density 0.001%

    No Known Activations