© 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. 90262
    Prev
    Next
    INDEX
    Explanations

    code and documentation

    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
     Friday
    -0.78
    基础
    -0.74
    直接
    -0.69
    乃是
    -0.68
     countries
    -0.67
     whereas
    -0.66
    bigcirc
    -0.65
    束
    -0.65
     星
    -0.65
    kamp
    -0.65
    POSITIVE LOGITS
    🉑
    0.76
    ebaran
    0.69
    長野
    0.69
    ACTION
    0.67
     GQ
    0.66
    フリー
    0.66
     Unterlagen
    0.65
    そこで
    0.65
    Outside
    0.63
     ACTION
    0.63
    Activations Density 0.058%

    No Known Activations