© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 260
    Prev
    Next
    INDEX
    Explanations

    directory paths with

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

    The neuron activates on numeric tokens (integer literals or digit sequences) in code and paths.

    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
     alcune
    -1.21
    ffective
    -0.94
    urten
    -0.94
    +}$
    -0.93
    ğer
    -0.91
     same
    -0.91
    ixel
    -0.90
    ύ
    -0.90
     famí
    -0.89
     abdic
    -0.89
    POSITIVE LOGITS
     our
    1.14
     and
    1.09
     before
    0.98
    잃
    0.95
     bronzo
    0.93
    ówczas
    0.93
    ेत्र
    0.92
     ویکی‌پدیا
    0.91
     咲
    0.91
    indsay
    0.91
    Activations Density 0.016%

    No Known Activations