© 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. 61
    Prev
    Next
    INDEX
    Explanations

    Chip (semiconductor, package, Kelly)

    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
    ↵
    -3.86
     and
    -2.81
    缡
    -2.59
    鶿
    -2.59
    隄
    -2.52
    梛
    -2.44
    I
    -2.39
    ⁛
    -2.38
     of
    -2.33
     撮っ
    -2.31
    POSITIVE LOGITS
    geſ
    3.41
    鋱
    3.41
    筇
    3.00
    atoren
    2.95
    ﮟ
    2.95
    ጺ
    2.88
     untuk
    2.88
    饪
    2.81
    How
    2.80
    卝
    2.77
    Activations Density 0.007%

    No Known Activations