© 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. 10-GEMMASCOPE-RES-131K
    7. 66351
    Prev
    Next
    INDEX
    Explanations

    `=========` placeholder

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

    The neuron flags occurrences of angle‐bracket tokens (e.g. “<>”) as used in code or formulas.

    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
    ↵↵
    -2.47
    HomeAsUpEnabled
    -1.98
    crollView
    -1.97
    酩
    -1.96
    displaymath
    -1.96
     neues
    -1.93
    肫
    -1.91
    艫
    -1.89
     včetně
    -1.88
    طبيق
    -1.88
    POSITIVE LOGITS
    栊
    2.09
     cũng
    2.00
    ا
    1.99
    y
    1.95
    am
    1.90
    ྕ
    1.88
     femenino
    1.81
    鯪
    1.81
    うちの
    1.80
    ㈮
    1.78
    Activations Density 0.006%

    No Known Activations