© 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. 10-GEMMASCOPE-RES-131K
    7. 70013
    Prev
    Next
    INDEX
    Explanations

    level and scale

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

    The neuron detects mentions of hierarchical extents, i.e. phrases like “on a X level” or “on a X scale.”

    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
    鈇
    -2.09
    efter
    -1.81
     การ์ตูน
    -1.73
     pentru
    -1.68
     lengte
    -1.67
    استفاده
    -1.67
    𖡼
    -1.67
    inspira
    -1.64
    鶲
    -1.62
     Mulher
    -1.61
    POSITIVE LOGITS
    n
    2.98
    (
    2.84
    o
    2.64
    p
    2.61
    s
    2.52
    5
    2.47
    ti
    2.45
    "
    2.41
    $
    2.30
    en
    2.28
    Activations Density 0.010%

    No Known Activations