© 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. 22-GEMMASCOPE-RES-131K
    7. 16352
    Prev
    Next
    INDEX
    Explanations

    , or, and

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

    The neuron activates on standalone numeric tokens and numeric literals (e.g. numbers in text or code).

    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
    本身
    -0.91
     FEDERAL
    -0.91
     SwitchCompat
    -0.88
     Frankrijk
    -0.87
     itself
    -0.86
     politiet
    -0.85
    yyy
    -0.85
     "\<
    -0.85
     giugno
    -0.85
     stesse
    -0.84
    POSITIVE LOGITS
    liśmy
    0.98
     a
    0.84
     Offers
    0.80
     buen
    0.79
     shiny
    0.79
     define
    0.78
     Extra
    0.78
    ihnachts
    0.77
    chemy
    0.76
    ggars
    0.76
    Activations Density 0.106%

    No Known Activations