© 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. 106418
    Prev
    Next
    INDEX
    Explanations

    report, Version, Include, text, sarcoma

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

    This neuron responds to mid-sentence capitalized tokens—that is, proper names, titles, or other internal words written with initial capitals rather than sentence-initial words.

    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
     seks
    -0.84
     maske
    -0.82
    šiu
    -0.82
     dios
    -0.80
    чення
    -0.79
    🥰
    -0.78
    addr
    -0.78
     selve
    -0.77
    лії
    -0.77
    сії
    -0.76
    POSITIVE LOGITS
     eclip
    0.87
     veik
    0.80
     interested
    0.80
    gls
    0.80
     afore
    0.77
     해
    0.77
     Glanz
    0.75
    ๗
    0.75
     świet
    0.74
     creativos
    0.74
    Activations Density 0.001%

    No Known Activations