© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 89987
    Prev
    Next
    INDEX
    Explanations

    Kevin Alexander

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

    This neuron detects the use of bracketed keys or indices in code (e.g. array or dictionary accesses like $lang['…']).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    zené
    -0.84
     Bauern
    -0.77
    کتر
    -0.76
    /**
    -0.72
    等于
    -0.71
    tensors
    -0.71
    Transcripción
    -0.70
    🅂
    -0.69
    LETE
    -0.68
     creep
    -0.68
    POSITIVE LOGITS
     TCA
    1.15
    TCA
    1.10
     СЕ
    0.84
     TS
    0.84
     Squash
    0.79
    tslib
    0.77
     Typo
    0.77
     Waite
    0.77
    TS
    0.75
    เท
    0.75
    Activations Density 0.004%

    No Known Activations