© 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. 6821
    Prev
    Next
    INDEX
    Explanations

    initiating/continuing operations

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

    The neuron detects numeric tokens that include decimal points (i.e. 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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    taking
    -1.89
     Dinas
    -1.74
    considering
    -1.71
     speciale
    -1.69
     Conſ
    -1.66
    trying
    -1.63
     fiches
    -1.63
    ఽ
    -1.59
     enthou
    -1.59
     Nieuwe
    -1.59
    POSITIVE LOGITS
    ↵↵
    2.58
     also
    2.19
     will
    2.06
     oddly
    1.95
     truly
    1.90
     strangely
    1.89
     may
    1.88
    ↵↵↵
    1.86
     markedly
    1.82
     might
    1.81
    Activations Density 0.167%

    No Known Activations