© 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. 63241
    Prev
    Next
    INDEX
    Explanations

    questions for points

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

    The neuron principally activates on numeric tokens (digits, numbers, and placeholders in math or selection contexts).

    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
     flavor
    -0.76
    بحث
    -0.74
    agua
    -0.74
    roon
    -0.72
     Must
    -0.72
    ök
    -0.71
    onchange
    -0.71
    tarta
    -0.71
    nowrap
    -0.71
     uży
    -0.71
    POSITIVE LOGITS
     BRAIN
    1.38
     brain
    1.23
     Brain
    1.20
    brainly
    1.11
    Brain
    1.05
    idiary
    0.97
    вір
    0.91
     hoped
    0.90
     remercie
    0.90
     armies
    0.87
    Activations Density 0.008%

    No Known Activations