© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 100645
    Prev
    Next
    INDEX
    Explanations

    file name assignment

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

    the variable or identifier "file_name" (or variations like "filename" and "File Name") in code and documents.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron selectively activates on occurrences of “file_name” (and closely related filename-like identifiers) in code snippets.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    ޏ
    -2.86
    鏵
    -2.56
    蕯
    -2.41
    蹓
    -2.36
     ſte
    -2.36
    تیجه
    -2.23
    Ᏺ
    -2.23
    綃
    -2.14
    鼱
    -2.11
    喼
    -2.11
    POSITIVE LOGITS
     You
    2.23
    裡的
    2.17
    緲
    2.00
     is
    1.97
    嚶
    1.94
    つなが
    1.91
     în
    1.88
    apatalk
    1.84
     pentru
    1.83
    ть
    1.80
    Activations Density 0.009%

    No Known Activations