© 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. 959
    Prev
    Next
    INDEX
    Explanations

    associated documentation files

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

    The neuron is tuned to detect standalone numeric tokens (sequences of digits) in the text.

    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
     proposent
    -0.69
    发言
    -0.67
     hefyd
    -0.67
     Ener
    -0.65
    创始
    -0.65
     fä
    -0.65
    ]+$
    -0.63
    创始人
    -0.63
    Halaman
    -0.62
     lower
    -0.61
    POSITIVE LOGITS
    ewel
    0.76
    സ്
    0.73
    ędz
    0.73
    料
    0.73
    NEG
    0.72
    Mach
    0.72
    estris
    0.71
     mana
    0.69
     হ
    0.69
    lader
    0.69
    Activations Density 0.084%

    No Known Activations