© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 106505
    Prev
    Next
    INDEX
    Explanations

    coding: utf-8 -*-

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

    The neuron activates on short technical abbreviations (e.g. “utf,” “url,” “EF”) typically found in code headers, metadata, or URL encoding.

    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
     becomes
    -0.91
     १
    -0.83
     known
    -0.80
    SizedBox
    -0.77
    LogFactory
    -0.77
    ͢
    -0.77
    tembro
    -0.76
     sierpnia
    -0.75
    ofType
    -0.75
    めている
    -0.74
    POSITIVE LOGITS
    めちゃ
    0.81
     Mysterious
    0.75
     maniac
    0.75
    turning
    0.74
    Conc
    0.74
     tři
    0.73
    点が
    0.73
     [
    0.73
     insom
    0.72
    SOURCES
    0.71
    Activations Density 0.001%

    No Known Activations