© 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. 32861
    Prev
    Next
    INDEX
    Explanations

    systemhigh-durability

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

    The neuron is triggered by numeric specification tokens (e.g. decimal or integer values in product specs).

    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
    dding
    -1.66
    alers
    -1.61
    quần
    -1.56
     variaciones
    -1.53
    其實
    -1.48
     mojej
    -1.48
     večer
    -1.48
    bicicleta
    -1.48
     hermosas
    -1.46
    ureusement
    -1.46
    POSITIVE LOGITS
     also
    1.45
    靭
    1.38
     palab
    1.37
     ڤ
    1.32
     TWITTER
    1.31
    \
    1.31
     wanda
    1.30
     emailAlready
    1.30
     with
    1.30
     塗装
    1.29
    Activations Density 0.060%

    No Known Activations