© 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. 25002
    Prev
    Next
    INDEX
    Explanations

    viewport initial-scale=

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

    This neuron detects numeric tokens (digits and numeric parameter values) in HTML metadata.

    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
    に出て
    -1.19
    akuya
    -1.13
    ctober
    -1.09
     silnika
    -1.05
     Pueden
    -1.05
    ΤΟ
    -1.05
     }],
    -1.05
     cerâmica
    -1.04
     instala
    -1.04
    <<"
    -1.04
    POSITIVE LOGITS
    Dile
    1.16
    曲を
    1.07
    Hva
    1.00
     produrre
    1.00
     تھے
    0.99
    曲は
    0.98
     offrire
    0.96
     ADI
    0.96
     trei
    0.96
     mantenere
    0.95
    Activations Density 0.004%

    No Known Activations