© 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. 67162
    Prev
    Next
    INDEX
    Explanations

    object instantiation new

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

    This neuron detects programming‐code tokens (e.g. function calls, operators, punctuation, numeric literals, and quoted strings).

    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
     about
    -1.66
     übri
    -1.59
     their
    -1.57
     always
    -1.56
    </em>
    -1.48
     (!__
    -1.46
     our
    -1.41
     Früchte
    -1.41
    一部
    -1.41
     zawsze
    -1.40
    POSITIVE LOGITS
     anum
    1.55
    égias
    1.31
    恶魔
    1.27
    isateurs
    1.27
    AS
    1.27
    他想
    1.26
    毁灭
    1.25
    OS
    1.23
    เกง
    1.21
    に行ってきました
    1.20
    Activations Density 0.148%

    No Known Activations