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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 12970
    Prev
    Next
    INDEX
    Explanations

    code snippets

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

    This neuron detects numeric literal tokens (integer or floating-point constants) in code.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    zembro
    -1.19
    Myself
    -1.09
    ὓ
    -1.09
    ⢱
    -1.03
     magasiner
    -1.02
    其妙
    -1.02
     vrou
    -1.01
     الکتر
    -1.00
    ﺲ
    -0.98
     plafon
    -0.98
    POSITIVE LOGITS
     not
    1.30
     only
    1.20
    ?
    1.15
     by
    1.11
     in
    1.06
     for
    1.04
     had
    0.99
     on
    0.99
     [
    0.97
     took
    0.97
    Activations Density 0.005%

    No Known Activations