© 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. 34-GEMMASCOPE-RES-131K
    7. 32194
    Prev
    Next
    INDEX
    Explanations

    che / ache endings

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

    This neuron detects letter sequences containing "che" or similar patterns in names, scientific terms, and place names.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    rame
    -0.84
    re
    -0.78
     Ursprung
    -0.73
    ASON
    -0.72
    remarks
    -0.72
    results
    -0.72
    rai
    -0.71
    ren
    -0.69
     remarked
    -0.68
    rably
    -0.68
    POSITIVE LOGITS
    CHE
    0.88
    ぇ
    0.85
    onsor
    0.84
    ОН
    0.80
    anı
    0.79
    ele
    0.78
     CHE
    0.78
    equation
    0.77
    isserie
    0.77
    ep
    0.77
    Activations Density 0.063%

    No Known Activations