© 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. 93045
    Prev
    Next
    INDEX
    Explanations

    data structure elements

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

    The neuron activates on numeric tokens—i.e. sequences of digits.

    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
    --
    -0.86
     zon
    -0.86
    urlopen
    -0.85
    ---
    -0.82
    ─
    -0.76
    宗
    -0.75
     滅
    -0.74
    Pdf
    -0.73
     locator
    -0.72
    kerk
    -0.71
    POSITIVE LOGITS
     –
    0.98
     -
    0.82
     industrias
    0.78
     spur
    0.78
     −
    0.76
    תּ
    0.75
     Witherspoon
    0.75
     =
    0.75
    hộp
    0.74
     negociaciones
    0.73
    Activations Density 0.296%

    No Known Activations