© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 38679
    Prev
    Next
    INDEX
    Explanations

    img.shields.io

    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_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
    ИН
    -0.80
    rü
    -0.72
    Indians
    -0.71
     ventricle
    -0.71
    াকে
    -0.69
    quea
    -0.69
    Lor
    -0.69
    PLY
    -0.68
    恐惧
    -0.68
    gambar
    -0.66
    POSITIVE LOGITS
     Anleitung
    0.74
    gnosis
    0.73
    empl
    0.71
     cabling
    0.68
    Ws
    0.68
    福井
    0.68
    pet
    0.68
     strata
    0.66
    sel
    0.65
    ado
    0.65
    Activations Density 0.028%

    No Known Activations