© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 14494
    Prev
    Next
    INDEX
    Explanations

    programming code snippets

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

    The neuron strongly fires on non-ordinary, domain-specific tokens—especially code identifiers or proper nouns (e.g. CamelCase API/class names).

    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
    杙
    -2.98
    厹
    -2.64
    眥
    -2.61
    臜
    -2.55
    氿
    -2.48
    耵
    -2.47
    狆
    -2.45
    あります
    -2.38
    諼
    -2.34
    现在的
    -2.33
    POSITIVE LOGITS
     was
    3.44
    ….
    3.02
     looks
    2.86
    …..
    2.73
    </h2>
    2.72
     ….
    2.70
    </em>
    2.69
    …
    2.58
    ,”
    2.56
     seems
    2.53
    Activations Density 0.004%

    No Known Activations