© 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. 69030
    Prev
    Next
    INDEX
    Explanations

    punctuated code structures

    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
    商场
    -1.52
     edile
    -1.51
    昨日の
    -1.48
     your
    -1.47
     アンド
    -1.38
    複数の
    -1.38
    近年来
    -1.37
     сча
    -1.36
    ちなみに
    -1.35
     麵
    -1.35
    POSITIVE LOGITS
    '
    1.79
     of
    1.63
    棡
    1.50
     จาก
    1.49
    ."
    1.47
    艽
    1.45
    其
    1.44
    下意识
    1.40
     way
    1.39
     její
    1.38
    Activations Density 0.004%

    No Known Activations