© 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. 22-GEMMASCOPE-RES-131K
    7. 130263
    Prev
    Next
    INDEX
    Explanations

    The neuron fires most strongly on the hyphenated term “live-action,” effectively detecting mentions of “live-action” films.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    previous / last

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    Cambios
    -0.86
    ȕ
    -0.83
    一惊
    -0.82
    hedrals
    -0.81
    plated
    -0.81
    ographers
    -0.79
    ʹ
    -0.79
    operating
    -0.79
    athons
    -0.78
    lese
    -0.77
    POSITIVE LOGITS
     previous
    2.03
     previously
    1.93
    เคย
    1.73
     last
    1.69
    上次
    1.59
    previous
    1.45
    曾
    1.28
    previously
    1.25
     sebelumnya
    1.25
    あの
    1.25
    Activations Density 0.130%

    No Known Activations