© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 129670
    Prev
    Next
    INDEX
    Explanations

    opening a window

    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
    ↵
    -1.84
     ”
    -1.31
    __("
    -1.30
     coming
    -1.24
    ↵↵
    -1.24
    outchouc
    -1.23
    inees
    -1.21
     like
    -1.21
     alchemy
    -1.20
    тиков
    -1.18
    POSITIVE LOGITS
     mangled
    1.45
    阋
    1.32
    änemark
    1.28
     ส์
    1.27
    いくつ
    1.27
     rapidez
    1.27
     BOTH
    1.26
    哢
    1.23
     rendement
    1.23
    喁
    1.23
    Activations Density 0.081%

    No Known Activations