© 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. 75776
    Prev
    Next
    INDEX
    Explanations

    http:// or https://

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

    The neuron strongly activates on tokens that are numbers, punctuation marks, or other non-alphabetic/symbolic fragments (e.g. digits, decimal numbers, commas, hyphens, apostrophes).

    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
    羽
    -0.88
     listopada
    -0.86
    perp
    -0.81
    `
    -0.78
    slidesPer
    -0.77
     grudnia
    -0.76
     czerwca
    -0.73
    ()['
    -0.73
    $("#
    -0.71
     principais
    -0.71
    POSITIVE LOGITS
    quadratic
    0.85
     specular
    0.78
    Kc
    0.76
     quadratic
    0.76
    ricos
    0.75
     打开
    0.74
     stedet
    0.73
    に伴
    0.73
    色んな
    0.73
    ようになりました
    0.73
    Activations Density 0.014%

    No Known Activations