© 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. 9330
    Prev
    Next
    INDEX
    Explanations

    separators like `*****` or `-----` before "Original"

    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
    s
    -3.48
    t
    -3.33
    '
    -2.91
    ’
    -2.70
    h
    -2.69
    k
    -2.64
     porsi
    -2.44
    ，“
    -2.33
     pasaran
    -2.28
     dostępne
    -2.22
    POSITIVE LOGITS
    ي
    2.80
    してました
    2.72
    </u>
    2.59
    ztes
    2.59
     souligné
    2.45
     інші
    2.44
    mẫu
    2.44
     categorically
    2.41
     например
    2.39
     única
    2.36
    Activations Density 0.013%

    No Known Activations