© 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. 10-GEMMASCOPE-RES-131K
    7. 39967
    Prev
    Next
    INDEX
    Explanations

    code and database

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

    This neuron detects numeric literals (integers or decimal 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_10/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
     which
    -2.14
     such
    -1.76
     vitally
    -1.73
     both
    -1.70
     innumerable
    -1.69
     including
    -1.66
     enormously
    -1.63
     poignant
    -1.60
     pertaining
    -1.59
     undoubtedly
    -1.57
    POSITIVE LOGITS
     formules
    1.76
     brune
    1.70
    zufügen
    1.69
     illustre
    1.68
     maniere
    1.67
    毟
    1.65
    硌
    1.65
     abonnement
    1.64
     pilotes
    1.62
     faciliter
    1.61
    Activations Density 0.258%

    No Known Activations