© 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. 12947
    Prev
    Next
    INDEX
    Explanations

    quotation markers and greetings

    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
     at
    -2.23
     on
    -2.03
     from
    -1.96
     in
    -1.76
     made
    -1.65
     over
    -1.63
     with
    -1.62
     by
    -1.55
     without
    -1.54
     four
    -1.53
    POSITIVE LOGITS
     haupts
    2.13
    玊
    1.73
     quintessential
    1.73
     overarching
    1.71
     unending
    1.71
     réserver
    1.70
     gesamten
    1.66
     certamente
    1.62
     soooo
    1.61
     établi
    1.61
    Activations Density 0.016%

    No Known Activations