© 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. 34-GEMMASCOPE-RES-131K
    7. 56840
    Prev
    Next
    INDEX
    Explanations

    cleave, clematis, clet

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

    This neuron primarily responds to numeric tokens, i.e. sequences of digits like street numbers, years, or other number strings.

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Nietzsche
    -0.85
     Luftwaffe
    -0.82
    warz
    -0.81
    went
    -0.80
    ⓘ
    -0.79
     yup
    -0.77
     Davids
    -0.76
    ത്ത
    -0.75
     ${{
    -0.75
     {#
    -0.72
    POSITIVE LOGITS
    閉店
    0.82
    教え
    0.79
     futile
    0.79
     Freunden
    0.74
    вої
    0.74
    >>,
    0.74
     cleave
    0.73
     hydrochloride
    0.73
     concise
    0.73
    一秒
    0.72
    Activations Density 0.065%

    No Known Activations