© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77234
    Prev
    Next
    INDEX
    Explanations

    question or statement markers

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

    The neuron strongly activates on punctuation and numeric/parameter tokens in technical spec‐style lists (e.g. commas, colons, parentheses, and adjacent numeric or attribute keywords in a specification).

    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
    亿美元
    -0.88
     circo
    -0.83
     November
    -0.80
     September
    -0.80
    部落
    -0.79
     chronologically
    -0.79
     supremely
    -0.79
     Gesund
    -0.78
     خاصی
    -0.77
    onais
    -0.76
    POSITIVE LOGITS
     ответы
    0.85
    alians
    0.85
     Doyle
    0.84
     courtyard
    0.83
    tová
    0.79
     outlines
    0.78
    ologische
    0.77
     dao
    0.76
     레이
    0.75
    цький
    0.75
    Activations Density 0.008%

    No Known Activations