© 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. 39904
    Prev
    Next
    INDEX
    Explanations

    quoted strings and structures

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

    The neuron activates on numeric literal tokens (numbers).

    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
    u
    -3.69
    e
    -3.63
    蹰
    -2.58
    却没有
    -2.50
    in
    -2.50
    y
    -2.45
    笮
    -2.38
     faſt
    -2.34
     frança
    -2.34
    _
    -2.31
    POSITIVE LOGITS
     When
    3.27
     This
    2.94
     französische
    2.59
    ?????
    2.52
     originalen
    2.48
     dampen
    2.44
    轳
    2.39
    錘
    2.38
    開口
    2.36
     normalen
    2.34
    Activations Density 0.007%

    No Known Activations