© 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. 70482
    Prev
    Next
    INDEX
    Explanations

    emojis and symbols

    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
     Two
    -2.14
     three
    -2.11
     eight
    -2.09
     TWO
    -2.02
     For
    -2.02
     after
    -2.02
     शुर
    -1.97
     two
    -1.94
     four
    -1.94
     ONLY
    -1.91
    POSITIVE LOGITS
     tinha
    1.91
    她的
    1.91
    AND
    1.73
     ferocious
    1.73
    which
    1.73
    whose
    1.72
    のは
    1.71
     blossoming
    1.70
     '"
    1.67
     …..
    1.67
    Activations Density 0.001%

    No Known Activations