© 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. 39507
    Prev
    Next
    INDEX
    Explanations

    quotation marks around attributes

    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
    ～」
    -1.01
    埕
    -1.00
     fuer
    -0.94
    见到
    -0.92
    ⁉
    -0.91
    +
    -0.90
    sendStatus
    -0.89
     venner
    -0.89
    ForKey
    -0.88
    ?”
    -0.87
    POSITIVE LOGITS
     to
    1.12
     gezwungen
    1.02
     sogget
    1.01
     Clim
    0.99
     gesammelt
    0.98
     subido
    0.95
     zugänglich
    0.95
     respectivos
    0.94
    你了
    0.94
    嬴
    0.94
    Activations Density 0.011%

    No Known Activations