© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 68376
    Prev
    Next
    INDEX
    Explanations

    sending google links or operator messages

    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
     for
    -1.16
     certainly
    -1.14
     without
    -1.13
     would
    -1.13
    nossa
    -1.12
    vård
    -1.11
    ”?
    -1.11
     not
    -1.07
     should
    -1.06
     three
    -1.06
    POSITIVE LOGITS
     your
    1.85
     you
    1.52
    ">!
    1.35
    ごちそうさまでした
    1.30
    ごちそう
    1.27
    皱眉
    1.27
    ご馳走
    1.25
    额头
    1.25
    撵
    1.23
     hlavně
    1.21
    Activations Density 0.002%

    No Known Activations