© 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. 100812
    Prev
    Next
    INDEX
    Explanations

    shell commands and pipes

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

    the pipe operator in shell scripts and command-line 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
    ’
    -2.33
     =
    -1.81
    ulate
    -1.67
    );
    -1.64
    s
    -1.64
    =“
    -1.60
     not
    -1.60
     $
    -1.59
    也被
    -1.55
    ’’
    -1.55
    POSITIVE LOGITS
    俛
    1.75
    媃
    1.73
     odpor
    1.73
     cadáver
    1.67
    archiviato
    1.66
    montre
    1.65
    Unione
    1.65
     zdan
    1.64
    成為
    1.64
    的時候
    1.64
    Activations Density 0.006%

    No Known Activations