© 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. 22-GEMMASCOPE-RES-131K
    7. 14358
    Prev
    Next
    INDEX
    Explanations

    URLs and file paths

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

    This neuron detects numeric tokens (sequences of digits), such as version numbers, list indices, package counts, and other digit‐only strings.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     initView
    -1.03
     település
    -1.01
     have
    -1.01
     aanzien
    -0.98
     helps
    -0.96
    ∣
    -0.95
     low
    -0.95
     sophisticated
    -0.94
     highly
    -0.94
     placed
    -0.94
    POSITIVE LOGITS
     ventes
    1.13
    orexia
    1.05
     allerlei
    1.05
     artig
    1.02
     aksesuar
    0.99
    licopter
    0.98
    outlined
    0.95
    potentially
    0.95
    ISTAS
    0.94
     lentamente
    0.94
    Activations Density 0.004%

    No Known Activations