© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 12673
    Prev
    Next
    INDEX
    Explanations

    plateau contexts

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

    The neuron is tuned to detect numeric tokens (numerical values and measurements) in the text.

    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
    螻
    -2.63
    粁
    -2.63
     ถ้า
    -2.45
    纐
    -2.39
     That
    -2.38
    驒
    -2.36
    ጳ
    -2.36
    ญี่ป
    -2.36
     เรา
    -2.31
    儅
    -2.23
    POSITIVE LOGITS
    '
    3.16
    A
    2.86
    F
    2.56
    <em>
    2.56
     of
    2.55
    𓋼
    2.52
    s
    2.42
    是非常
    2.39
     that
    2.34
    It
    2.25
    Activations Density 0.006%

    No Known Activations