© 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. 11536
    Prev
    Next
    INDEX
    Explanations

    code syntax elements

    np_acts-logits-general · gemini-2.5-flash-lite

    closing parentheses, brackets, or braces in programming code.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
    0
    -4.50
    6
    -4.34
    7
    -4.19
    4
    -4.06
    9
    -3.98
    8
    -3.66
    3
    -3.56
    What
    -3.47
    Compared
    -3.27
    However
    -3.25
    POSITIVE LOGITS
    晅
    3.38
    荦
    3.20
    ⟝
    3.17
    ']>
    3.16
    洳
    3.02
    ৄ
    3.02
    y
    2.97
    逖
    2.94
    🪬
    2.88
    ﮏ
    2.88
    Activations Density 0.007%

    No Known Activations