© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 93242
    Prev
    Next
    INDEX
    Explanations

    licensing and code comments

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

    The neuron activates on standalone numeric tokens (sequences of digits) in code or markup.

    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
    eda
    -0.73
     इं
    -0.72
    interno
    -0.72
     senang
    -0.71
     glyph
    -0.69
    сете
    -0.69
    bower
    -0.68
    шена
    -0.68
    чам
    -0.68
    الغ
    -0.68
    POSITIVE LOGITS
    crever
    0.81
    щиеся
    0.81
    icium
    0.80
     Sully
    0.73
    rashed
    0.73
     ravaged
    0.73
    Tratamiento
    0.73
     Kendal
    0.72
     Regis
    0.72
    hamb
    0.72
    Activations Density 0.008%

    No Known Activations