© 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. 98603
    Prev
    Next
    INDEX
    Explanations

    Roman de la Rose

    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
     cut
    -0.75
     konuş
    -0.72
     Message
    -0.70
     make
    -0.68
    raw
    -0.67
     Wirtschafts
    -0.67
     antitrust
    -0.66
    힌
    -0.66
    労
    -0.66
     دادن
    -0.66
    POSITIVE LOGITS
    ٱ
    0.82
    promis
    0.81
     airbag
    0.81
    javas
    0.75
    Lond
    0.75
    senior
    0.75
    Salva
    0.74
    semic
    0.73
    ennent
    0.73
    Timothy
    0.73
    Activations Density 0.009%

    No Known Activations