© 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. 32931
    Prev
    Next
    INDEX
    Explanations

    individual resources, biopsy of, conditions for, NMR line

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

    words or concepts related to technical procedures, installations, or established protocols.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    This neuron activates on numeric measurements or quantities (numbers and associated units/values) mentioned in the text.

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     juſ
    -1.38
     réinitial
    -1.32
     ſp
    -1.30
    衚
    -1.27
     compromisos
    -1.27
     ſur
    -1.27
     fidé
    -1.26
     délais
    -1.24
     faciliter
    -1.24
     publicités
    -1.24
    POSITIVE LOGITS
     will
    1.53
     should
    1.47
     could
    1.46
     can
    1.45
     at
    1.41
     for
    1.36
     dazzling
    1.35
     neatly
    1.32
     in
    1.29
     as
    1.24
    Activations Density 0.079%

    No Known Activations