© 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. 10-GEMMASCOPE-RES-131K
    7. 73621
    Prev
    Next
    INDEX
    Explanations

    full-size or full-length descriptor

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

    The neuron activates on numeric scale or size descriptors (e.g. “full-scale,” “life-size,” “full-length”) indicating measurements or dimensions.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    鹀
    -2.14
    どうやって
    -1.63
    犼
    -1.59
    ܃
    -1.59
     eenvou
    -1.57
    了个
    -1.55
    鸕
    -1.55
    撣
    -1.52
    geſ
    -1.49
    媼
    -1.49
    POSITIVE LOGITS
    on
    1.98
    ですが
    1.94
    。“
    1.82
    Certainly
    1.78
     αυτή
    1.73
     deine
    1.70
    と
    1.70
    ”？
    1.65
    ведите
    1.65
    hoenix
    1.65
    Activations Density 0.012%

    No Known Activations