© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77056
    Prev
    Next
    INDEX
    Explanations

    technical domain terms

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

    The neuron primarily activates on numeric tokens (digits and numbers, including version numbers).

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

    No Comments

    Negative Logits
    ABOR
    -0.71
    pev
    -0.70
    וס
    -0.70
    xie
    -0.66
     étoit
    -0.66
    менение
    -0.66
     Merr
    -0.65
     sabar
    -0.64
    Tradition
    -0.64
     Геор
    -0.64
    POSITIVE LOGITS
     যে
    0.67
     tež
    0.65
     dialysis
    0.64
    clim
    0.64
    ellingham
    0.63
    LIBRA
    0.63
    мети
    0.62
    ESR
    0.61
    倒
    0.61
    Ǣ
    0.60
    Activations Density 0.030%

    No Known Activations