© 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. 1115
    Prev
    Next
    INDEX
    Explanations

    publication history

    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
    -2.88
    鹛
    -2.84
    硨
    -2.78
    镦
    -2.64
    栊
    -2.56
    𞤢
    -2.45
    毉
    -2.41
    杁
    -2.39
    耵
    -2.34
    蒾
    -2.33
    POSITIVE LOGITS
    इटम
    2.86
    浤
    2.53
    但是
    2.45
    塤
    2.45
    ن
    2.36
    ”，
    2.31
    ஂ
    2.30
    en
    2.30
    n
    2.28
     “[
    2.25
    Activations Density 0.007%

    No Known Activations