© 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. 84550
    Prev
    Next
    INDEX
    Explanations

    input fields and interactive elements

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

    The neuron never fires—it does not reliably detect any of the shown tokens.

    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
    0
    -2.06
    臯
    -1.88
    7
    -1.84
    着一
    -1.83
     to
    -1.75
    基本上
    -1.73
    并没有
    -1.71
     beschränkt
    -1.70
     wiederholt
    -1.69
     hauptsächlich
    -1.68
    POSITIVE LOGITS
    the
    1.98
    浤
    1.90
     ehemal
    1.87
     luch
    1.73
    alakip
    1.72
     supaya
    1.71
    +"&
    1.71
     dapat
    1.70
     manajemen
    1.70
    櫟
    1.67
    Activations Density 0.009%

    No Known Activations