© 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. 11843
    Prev
    Next
    INDEX
    Explanations

    Oropharyngeal, holocentric, urodynamic

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

    scientific prefixes like "holo", "oro", "uro" that appear in technical or biological terms.

    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
    ču
    -0.80
    そう
    -0.78
    emplace
    -0.76
    TURE
    -0.76
    ladung
    -0.72
    $",
    -0.72
     Cister
    -0.71
    ང་
    -0.71
    (≧
    -0.71
    wish
    -0.70
    POSITIVE LOGITS
     prend
    0.79
    нак
    0.75
    Coun
    0.73
    filesystem
    0.69
     Jelly
    0.69
     nasal
    0.66
     feat
    0.66
    rada
    0.65
    atly
    0.64
     daran
    0.64
    Activations Density 0.031%

    No Known Activations