© 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. 30175
    Prev
    Next
    INDEX
    Explanations

    since history

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

    This neuron activates mainly on HTML/XML tags and numeric tokens (digits, punctuation used in numbering).

    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
     especially
    -1.00
     meses
    -0.96
     tutto
    -0.95
     principales
    -0.95
     “
    -0.95
     particularly
    -0.93
     at
    -0.91
    ueras
    -0.90
    主要
    -0.89
     primarily
    -0.89
    POSITIVE LOGITS
     since
    1.75
    Only
    1.60
    only
    1.52
     only
    1.47
     history
    1.45
    since
    1.44
    Since
    1.43
    Historically
    1.34
     seuls
    1.33
     precedent
    1.31
    Activations Density 0.080%

    No Known Activations