© 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. 84867
    Prev
    Next
    INDEX
    Explanations

    license identifiers and structure

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

    This neuron activates on numeric tokens and numeric sequences (digits and numbers) 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
     hoeft
    -0.81
    pright
    -0.75
     consultez
    -0.74
    裢
    -0.73
    rière
    -0.73
    ∪
    -0.72
     senza
    -0.72
    hoff
    -0.71
    świet
    -0.70
    звичай
    -0.70
    POSITIVE LOGITS
    seler
    0.77
    音声
    0.73
    Lorraine
    0.66
     управ
    0.65
     decadent
    0.63
     deplorable
    0.62
    Sessions
    0.62
     dielectric
    0.61
     ચ
    0.60
    escrit
    0.60
    Activations Density 0.053%

    No Known Activations