© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 91552
    Prev
    Next
    INDEX
    Explanations

    Q&A format

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

    The neuron activates on numeric tokens (e.g. standalone numbers or numbers within URLs and version strings).

    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
    ACCIÓN
    -0.82
    lijken
    -0.74
    يارة
    -0.67
     intelligence
    -0.67
    约会
    -0.66
    ilität
    -0.66
    ∵
    -0.66
    brett
    -0.65
     tup
    -0.65
    ровали
    -0.65
    POSITIVE LOGITS
    efte
    0.89
    essero
    0.81
    ThroughAttribute
    0.79
    ิ่น
    0.79
    Cited
    0.78
     آخر
    0.77
    othed
    0.76
    álva
    0.75
    volved
    0.75
    нім
    0.74
    Activations Density 0.000%

    No Known Activations