© 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. 22-GEMMASCOPE-RES-131K
    7. 25196
    Prev
    Next
    INDEX
    Explanations

    attribution and news sources

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

    This neuron fires on standalone numeric tokens with decimal points (floating-point numbers).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     baku
    -1.00
     trenger
    -0.97
     kumar
    -0.94
     jaya
    -0.93
     kras
    -0.92
     palazzo
    -0.91
     umo
    -0.91
     vore
    -0.90
     himo
    -0.90
     monaco
    -0.90
    POSITIVE LOGITS
     fortale
    1.18
     (!_
    1.16
     podczas
    1.15
    (!_
    1.11
     sustancias
    1.05
     ها
    1.01
    část
    1.00
    Groet
    0.99
    ambut
    0.98
     administrar
    0.98
    Activations Density 0.000%

    No Known Activations