© 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. 34-GEMMASCOPE-RES-131K
    7. 97925
    Prev
    Next
    INDEX
    Explanations

    code delimiters and symbols

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

    The neuron fires on numeric tokens—digits or numbers (e.g. version numbers, years, IDs) embedded anywhere in the 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_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
    以来
    -0.68
    ForAll
    -0.67
     AW
    -0.65
    披露
    -0.65
     包
    -0.65
     Auftrag
    -0.63
    
    -0.63
     cốc
    -0.63
     abgerufen
    -0.62
    ImageContext
    -0.62
    POSITIVE LOGITS
     biodegradable
    0.71
     Donate
    0.69
    inton
    0.69
    phosphat
    0.68
     attacked
    0.68
    weis
    0.68
    🍅
    0.68
    ition
    0.67
     beep
    0.67
    เท
    0.66
    Activations Density 0.073%

    No Known Activations