© 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. 10041
    Prev
    Next
    INDEX
    Explanations

    build instructions and code snippets

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

    line continuation characters (backslashes) in code, particularly in configuration files and build scripts.

    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
    providedIn
    -2.83
    '
    -2.75
    Ꮉ
    -2.31
     italie
    -2.19
     vinil
    -2.19
     Septembre
    -2.16
     maillot
    -2.09
    浥
    -2.08
     pourcentage
    -2.06
     Octobre
    -2.06
    POSITIVE LOGITS
     There
    2.31
    er
    2.23
    s
    2.08
    1
    2.06
    ti
    2.05
    y
    2.00
    4
    1.98
    6
    1.95
    w
    1.92
     It
    1.91
    Activations Density 0.012%

    No Known Activations