© 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. 36689
    Prev
    Next
    INDEX
    Explanations

    special characters and punctuation

    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
     induk
    -1.71
    genen
    -1.68
     Kristus
    -1.63
     Agreg
    -1.62
     kompati
    -1.58
     Ministre
    -1.57
     labdar
    -1.55
     花朵
    -1.51
    ĭ
    -1.49
     aéro
    -1.48
    POSITIVE LOGITS
     to
    1.66
    UCIÓN
    1.44
     get
    1.41
     use
    1.35
     that
    1.33
     now
    1.31
     will
    1.30
     until
    1.30
     C
    1.29
     used
    1.29
    Activations Density 0.014%

    No Known Activations