© 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. 118893
    Prev
    Next
    INDEX
    Explanations

    copyright notices and licenses

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

    The neuron activates on numeric tokens (e.g. years, versions, error codes).

    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
     GIL
    -0.75
     Skipper
    -0.75
     PAM
    -0.74
     viewModel
    -0.73
    Mime
    -0.73
    EYE
    -0.70
     propo
    -0.69
     Instru
    -0.67
    committee
    -0.66
     Hallo
    -0.66
    POSITIVE LOGITS
     driver
    0.77
    とし
    0.73
    ▐
    0.71
     drivers
    0.68
    vend
    0.68
    Ⅳ
    0.67
     swings
    0.67
     reserves
    0.67
    oys
    0.67
    δέ
    0.66
    Activations Density 0.047%

    No Known Activations