© 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. 91918
    Prev
    Next
    INDEX
    Explanations

    boolean assignments

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

    The neuron activates on numeric literals and number‐like tokens (e.g. integers, floats, flags) in 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_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
    劉
    -0.78
    الأ
    -0.73
    كان
    -0.73
    itanya
    -0.72
     rien
    -0.72
    ifornie
    -0.70
     okhttp
    -0.69
    ק
    -0.69
    Не
    -0.68
    Ти
    -0.68
    POSITIVE LOGITS
     YES
    2.70
     yes
    2.36
    YES
    2.23
     Yes
    2.02
    yes
    1.83
     NO
    1.80
    Yes
    1.59
    NO
    1.52
     yeah
    1.43
     YEAH
    1.39
    Activations Density 0.012%

    No Known Activations