© 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. 64948
    Prev
    Next
    INDEX
    Explanations

    terms of use

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

    This neuron detects numeric tokens—years, version numbers, numeric sequences, and related digits in code comments and boilerplate.

    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
     sold
    -0.87
    sold
    -0.75
    меча
    -0.68
    Zee
    -0.66
    element
    -0.66
     sunny
    -0.65
    Sold
    -0.65
     hiatus
    -0.65
    龄
    -0.64
    ラダ
    -0.63
    POSITIVE LOGITS
    ตาม
    0.69
    WHERE
    0.69
    Ratio
    0.67
    repair
    0.66
     Integer
    0.66
    句話
    0.64
     Finger
    0.63
    where
    0.63
    rü
    0.63
     Eph
    0.63
    Activations Density 0.047%

    No Known Activations