© 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. 34-GEMMASCOPE-RES-131K
    7. 57591
    Prev
    Next
    INDEX
    Explanations

    submitted with dates

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

    The neuron flags tokens that look like bits of programming code—identifiers (e.g. “express,” “router”), comment markers (e.g. “*/”), numeric literals, XML‐attribute numbers, etc.

    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
     Whitehall
    -0.72
    Interrupt
    -0.71
    utu
    -0.70
    Ata
    -0.69
    āh
    -0.68
    dataArray
    -0.68
     Aves
    -0.67
    newData
    -0.67
     Congress
    -0.66
    重视
    -0.65
    POSITIVE LOGITS
     Stacey
    0.70
    Pranala
    0.69
    čar
    0.67
    alnız
    0.67
    itaries
    0.66
     fliegen
    0.65
    鍵
    0.65
    懺
    0.64
     erfaren
    0.64
    collider
    0.64
    Activations Density 0.040%

    No Known Activations