© 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. 22-GEMMASCOPE-RES-131K
    4. 14810
    Prev
    Next
    INDEX
    Explanations

    programming data types

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

    This neuron detects occurrences of the programming-language string type token (e.g. “String” or “string”) in code.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    をしました
    -1.22
    GRect
    -1.18
    際に
    -1.16
    哙
    -1.13
    をお願い
    -1.13
    readFileSync
    -1.10
     zijne
    -1.09
    で使用
    -1.05
    あぁ
    -1.05
     ใหม่
    -1.05
    POSITIVE LOGITS
     on
    1.24
    前は
    1.09
    を
    1.05
    </h3>
    1.02
    実現
    0.97
     notes
    0.96
    l
    0.96
    asties
    0.95
    f
    0.94
    k
    0.92
    Activations Density 0.002%

    No Known Activations