© 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. 103936
    Prev
    Next
    INDEX
    Explanations

    code, imports, and programming

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

    The neuron detects numerical tokens, i.e. occurrences of numbers or numeric literals.

    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
    ставьте
    -0.77
    äumt
    -0.69
     Vickers
    -0.68
     gestaltet
    -0.66
    Personas
    -0.66
     점
    -0.66
    Alignment
    -0.66
    Borrar
    -0.66
     precede
    -0.66
    Marcel
    -0.65
    POSITIVE LOGITS
    import
    0.89
    ثمان
    0.82
     cookie
    0.79
     import
    0.77
    !
    0.75
    зонта
    0.74
     vendor
    0.73
    ajax
    0.72
    -!
    0.71
    udp
    0.71
    Activations Density 0.005%

    No Known Activations