© 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. 83394
    Prev
    Next
    INDEX
    Explanations

    examinations and trials

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

    This neuron detects programming‐code tokens, especially function and control‐structure identifiers (e.g. “have,” “posts,” “public,” “function”).

    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
     Etienne
    -0.75
    zee
    -0.73
     pleaf
    -0.71
    ]\
    -0.71
    ịch
    -0.71
    Etienne
    -0.71
    APON
    -0.69
    Mfg
    -0.69
     discriminación
    -0.69
    structured
    -0.68
    POSITIVE LOGITS
     Examinations
    0.84
     examinations
    0.82
     Exam
    0.76
     exam
    0.76
     peat
    0.74
     trial
    0.73
     examination
    0.72
     Trial
    0.71
     swings
    0.70
     exams
    0.68
    Activations Density 0.066%

    No Known Activations