© 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. 45556
    Prev
    Next
    INDEX
    Explanations

    what do you mean by

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

    This neuron activates on numeric tokens expressing non‐integer (decimal) values.

    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
     you
    -2.16
    e
    -1.98
     I
    -1.88
     on
    -1.79
     utilizando
    -1.70
     The
    -1.69
     It
    -1.66
    -
    -1.66
     are
    -1.66
     there
    -1.64
    POSITIVE LOGITS
    ]}$
    2.13
    bandicam
    1.91
     guir
    1.90
     banane
    1.82
     dij
    1.80
     JOSÉ
    1.79
     soie
    1.78
    栻
    1.77
    ності
    1.75
     DÉ
    1.75
    Activations Density 0.057%

    No Known Activations