© 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. 91753
    Prev
    Next
    INDEX
    Explanations

    drawing templates or PDFs

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

    The neuron fires on version‐number patterns (sequences of digits and dots, e.g. “2.0.1”).

    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
    墻
    -0.79
    SLS
    -0.79
     quyền
    -0.78
    Bacteria
    -0.75
    ⓘ
    -0.74
    TEXTURE
    -0.73
    צבע
    -0.73
    ély
    -0.73
    iov
    -0.72
    ენ
    -0.71
    POSITIVE LOGITS
     draw
    0.84
     oblast
    0.80
    <sub>
    0.77
    muje
    0.77
    draw
    0.77
    öll
    0.77
     Assisi
    0.75
    miljø
    0.75
     Draw
    0.75
    Draw
    0.75
    Activations Density 0.026%

    No Known Activations