© 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. 58354
    Prev
    Next
    INDEX
    Explanations

    legal and technical documents

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

    The neuron fires on numeric tokens and numeric literals (including integers, decimals, and negative numbers) wherever they appear.

    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
     Henk
    -0.71
    عه
    -0.70
     дело
    -0.65
    評価
    -0.65
     tableware
    -0.64
    langes
    -0.63
    chata
    -0.63
     funded
    -0.63
    筛
    -0.63
    чак
    -0.62
    POSITIVE LOGITS
     democracy
    0.84
     wretched
    0.73
     CONCEP
    0.72
     conference
    0.71
     weddings
    0.69
     ocasión
    0.69
     conferences
    0.67
     gowns
    0.67
    Names
    0.66
     accountability
    0.66
    Activations Density 0.062%

    No Known Activations