© 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. 30577
    Prev
    Next
    INDEX
    Explanations

    code preamble

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

    The neuron activates on numeric tokens—i.e. any standalone numbers or digit sequences (version numbers, counts, statistics, etc.).

    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
    GroupName
    -0.68
    ⦿
    -0.67
    견
    -0.67
    けどね
    -0.66
    TestId
    -0.66
     occult
    -0.63
    RegressionTest
    -0.63
    国会
    -0.63
    null
    -0.62
    ebvre
    -0.62
    POSITIVE LOGITS
    特朗
    0.78
    Lion
    0.70
    commodations
    0.69
     הרי
    0.66
     máximo
    0.65
    iths
    0.65
    jasper
    0.65
     výro
    0.64
    стый
    0.63
    询
    0.63
    Activations Density 0.045%

    No Known Activations