© 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. 34-GEMMASCOPE-RES-131K
    7. 83107
    Prev
    Next
    INDEX
    Explanations

    product description, mammography, REGISTRY, karaoke, bandstand, azure pipeline

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

    The neuron primarily detects single‐quote/apostrophe characters 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_34/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
    cello
    -0.70
     unserem
    -0.69
     FIXME
    -0.68
    ធ
    -0.67
     Continue
    -0.67
     McColl
    -0.67
    αιν
    -0.66
    linson
    -0.66
    mann
    -0.66
     asshole
    -0.65
    POSITIVE LOGITS
     clears
    0.84
    ɕ
    0.81
     beat
    0.79
    Judge
    0.77
    judge
    0.77
    lics
    0.76
    മ്
    0.76
     clearing
    0.76
     judgement
    0.75
     miliar
    0.75
    Activations Density 0.000%

    No Known Activations