© 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. 58838
    Prev
    Next
    INDEX
    Explanations

    Sanford news

    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
    pedido
    -0.81
     crescere
    -0.75
     sorgfältig
    -0.75
    veria
    -0.75
    atteindre
    -0.74
     möglichst
    -0.72
     VERB
    -0.69
     Allegro
    -0.69
    zeugung
    -0.69
     ^
    -0.68
    POSITIVE LOGITS
     suerte
    0.79
    塞
    0.75
    款
    0.75
    getWidth
    0.75
    Gew
    0.70
     Sass
    0.70
    吸引
    0.69
     ориенти
    0.69
    了一句
    0.68
    sete
    0.68
    Activations Density 0.045%

    No Known Activations