© 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. 32766
    Prev
    Next
    INDEX
    Explanations

    numerical sequences

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

    The neuron never activates on any of the presented tokens—i.e. it currently finds no patterns in these examples.

    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
    Jenis
    -2.03
     fidé
    -1.93
     biela
    -1.85
     refroid
    -1.72
    según
    -1.70
    dónde
    -1.70
     obuv
    -1.68
    lji
    -1.66
     vôtre
    -1.66
     démoc
    -1.64
    POSITIVE LOGITS
     a
    1.78
     can
    1.60
    D
    1.50
    K
    1.49
    '
    1.48
    T
    1.48
    O
    1.44
     to
    1.42
    H
    1.42
    N
    1.41
    Activations Density 0.034%

    No Known Activations