© 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. 70754
    Prev
    Next
    INDEX
    Explanations

    date/number after colon

    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
    nsyn
    -0.83
    äsident
    -0.77
    dtm
    -0.76
    úly
    -0.76
    ản
    -0.75
     править
    -0.74
     bingung
    -0.73
    agisse
    -0.72
     sfondo
    -0.72
    ᧐
    -0.71
    POSITIVE LOGITS
     until
    2.25
     till
    1.85
    until
    1.66
     jusqu
    1.63
     lasted
    1.52
     μέχρι
    1.41
     hasta
    1.37
    直至
    1.37
     até
    1.33
     UNTIL
    1.28
    Activations Density 0.107%

    No Known Activations