© 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. 10-GEMMASCOPE-RES-131K
    7. 42454
    Prev
    Next
    INDEX
    Explanations

    a sequence of specific concepts or titles

    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_10/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
    o
    -2.73
    T
    -2.72
    .”
    -2.66
    A
    -2.52
     尔
    -2.50
    K
    -2.48
    IN
    -2.39
    L
    -2.36
    ―――
    -2.33
    最初の
    -2.31
    POSITIVE LOGITS
     "
    2.50
    vantaged
    2.33
    ’
    2.30
    ’)
    2.30
    følgelig
    2.27
     aña
    2.16
    куда
    2.16
    虓
    2.14
    ла
    2.11
     három
    2.11
    Activations Density 0.000%

    No Known Activations