© 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. 34913
    Prev
    Next
    INDEX
    Explanations

    git pull origin

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

    The neuron fires on numeric literals (tokens composed of digits) wherever they appear in code or 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_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
    віти
    -0.84
     лист
    -0.80
     Erinnerungen
    -0.79
    truly
    -0.78
     reconocidos
    -0.78
     souver
    -0.77
     INTEREST
    -0.75
    seems
    -0.75
     Toutes
    -0.74
    held
    -0.74
    POSITIVE LOGITS
    OffsetY
    0.98
    ”？
    0.86
     or
    0.85
     berlina
    0.82
     atau
    0.81
    פשר
    0.81
     showed
    0.80
     establishing
    0.79
    Törté
    0.79
     Umb
    0.78
    Activations Density 0.003%

    No Known Activations