© 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. 2274
    Prev
    Next
    INDEX
    Explanations

    code snippets and markup

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

    The neuron activates on any token containing digits (e.g. version numbers, years, numeric parameters, codes).

    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
    няют
    -0.85
    bled
    -0.81
    StackTrace
    -0.73
    anel
    -0.72
     Hes
    -0.71
    Chosen
    -0.70
     yerde
    -0.69
    full
    -0.69
     Gerichte
    -0.68
    haired
    -0.68
    POSITIVE LOGITS
     Himalayas
    0.70
     sightings
    0.69
    atief
    0.69
     bott
    0.69
    Shapes
    0.69
     perjury
    0.67
    нением
    0.67
     underta
    0.67
     Twins
    0.67
    adería
    0.67
    Activations Density 0.044%

    No Known Activations