© 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. 10-GEMMASCOPE-RES-131K
    7. 38696
    Prev
    Next
    INDEX
    Explanations

    programming and numerical data

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

    The neuron activates on numeric tokens that include a decimal point (floating‐point literals).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     the
    -2.44
    7
    -2.06
    8
    -1.87
    5
    -1.84
     homicidio
    -1.79
    6
    -1.79
    4
    -1.73
     всех
    -1.66
     to
    -1.65
    2
    -1.63
    POSITIVE LOGITS
     mélang
    1.88
    jenige
    1.77
     réduit
    1.66
    espół
    1.62
    äts
    1.62
    adır
    1.62
    <bos>
    1.60
     récomp
    1.59
     coû
    1.59
    erialized
    1.59
    Activations Density 0.014%

    No Known Activations