© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 9638
    Prev
    Next
    INDEX
    Explanations

    version numbers and code identifiers

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

    The neuron activates on numeric tokens—digits, numbers, and numeric literals (e.g. version numbers, IDs, constants) embedded in code or 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_10/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
     schlaf
    -1.57
     in
    -1.41
     each
    -1.34
     during
    -1.25
     besonderen
    -1.23
     every
    -1.23
     have
    -1.21
     Näch
    -1.21
    inverno
    -1.20
     frischen
    -1.20
    POSITIVE LOGITS
     Alpes
    1.49
    quartered
    1.48
     baie
    1.44
    accharide
    1.42
    datable
    1.38
    Élet
    1.37
    сут
    1.35
    roxene
    1.34
    QMetaType
    1.34
    dass
    1.33
    Activations Density 0.015%

    No Known Activations