© 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. 39530
    Prev
    Next
    INDEX
    Explanations

    file/available/to/should/complicated/all/datastore/shows/device/also/Q followed by specific tokens

    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
     moverse
    -1.15
    予定です
    -1.13
    ところに
    -1.09
    Stamina
    -1.08
    reathable
    -1.07
     costado
    -1.07
     oído
    -1.06
    ができます
    -1.05
     juguete
    -1.05
    をしていた
    -1.04
    POSITIVE LOGITS
     even
    1.62
    even
    1.41
     again
    1.40
     also
    1.34
     incluso
    1.33
    l
    1.27
     since
    1.27
    in
    1.26
     даже
    1.23
     especially
    1.16
    Activations Density 0.013%

    No Known Activations