© 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. 25115
    Prev
    Next
    INDEX
    Explanations

    `se[0]`

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

    The neuron primarily activates on decimal numeric literals (floating‐point numbers).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     अगर
    -0.97
    jiri
    -0.94
    ällningar
    -0.91
     dueño
    -0.87
     paznok
    -0.87
     شناسی
    -0.85
     linho
    -0.85
    ridescent
    -0.84
     TÉCN
    -0.84
    班级
    -0.80
    POSITIVE LOGITS
     or
    1.11
     by
    1.02
     to
    0.96
    罡
    0.95
    ناول
    0.94
     will
    0.94
     stages
    0.94
     there
    0.93
    olybdenum
    0.88
     stage
    0.87
    Activations Density 0.000%

    No Known Activations