© 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. 116182
    Prev
    Next
    INDEX
    Explanations

    user profile information

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

    The neuron fires on numeric or quantitative tokens—things like ranks, IDs, counts, scores, dates, and other numbers.

    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
    epsilon
    -0.75
    mez
    -0.74
     functor
    -0.74
     градусов
    -0.74
     grocery
    -0.73
    чья
    -0.72
    的味道
    -0.69
     slave
    -0.69
     тест
    -0.69
     addr
    -0.69
    POSITIVE LOGITS
     profile
    1.77
    profile
    1.45
    Profile
    1.34
     Profile
    1.34
     profiles
    1.24
    profiles
    1.21
     level
    1.18
    level
    1.17
    Profil
    1.13
     profil
    1.13
    Activations Density 0.028%

    No Known Activations