© 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. 90792
    Prev
    Next
    INDEX
    Explanations

    code and programming constants

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

    The neuron activates on numeric literal tokens (e.g. 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_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
     with
    -1.88
     will
    -1.53
         
    -1.47
    gün
    -1.46
    letto
    -1.44
    籐
    -1.41
    ISATION
    -1.39
     computa
    -1.38
    remaining
    -1.34
    tığı
    -1.34
    POSITIVE LOGITS
    ’
    1.71
    acidad
    1.49
    :</
    1.45
     infolge
    1.42
     they
    1.41
    蹰
    1.38
     prüfen
    1.35
     hierzu
    1.34
    ?,?,
    1.34
     общественного
    1.33
    Activations Density 0.021%

    No Known Activations