© 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. 103468
    Prev
    Next
    INDEX
    Explanations

    `str`, `double`, `write`, `FileName`, `time`

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

    programming-related tokens, particularly function names, method calls, and technical identifiers in 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
    <bos>
    -1.71
     ist
    -1.50
    啱
    -1.45
    (
    -1.45
     The
    -1.44
    those
    -1.43
    开始
    -1.42
     and
    -1.41
    찮
    -1.39
    になった
    -1.38
    POSITIVE LOGITS
    इटम
    1.60
    𝕋
    1.55
    洇
    1.55
    踭
    1.49
    龵
    1.48
     場面
    1.46
    wała
    1.45
    袮
    1.44
    isée
    1.44
    RODUCTION
    1.41
    Activations Density 0.010%

    No Known Activations