© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 92626
    Prev
    Next
    INDEX
    Explanations

    creating new instances

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

    The neuron detects numeric literal tokens (i.e. numbers) 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
     humanidade
    -0.97
     também
    -0.87
     identidade
    -0.82
     coleção
    -0.79
     arquitetura
    -0.79
     [];
    -0.77
     indústria
    -0.75
    youts
    -0.75
    łej
    -0.75
    judice
    -0.74
    POSITIVE LOGITS
    llingen
    0.89
     View
    0.84
    ране
    0.84
     Optics
    0.80
     Salinity
    0.78
    my
    0.77
    mitian
    0.77
    <blockquote>
    0.77
    DoubleClick
    0.77
    View
    0.76
    Activations Density 0.001%

    No Known Activations