© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64844
    Prev
    Next
    INDEX
    Explanations

    programming code and scientific text

    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
    ząca
    -0.78
     seeding
    -0.78
     tehdä
    -0.72
    واسطة
    -0.71
     yelled
    -0.68
    meln
    -0.68
    ften
    -0.68
    ywna
    -0.68
    ener
    -0.67
     Pears
    -0.67
    POSITIVE LOGITS
    niko
    0.66
     маршру
    0.66
    mason
    0.65
    隙間
    0.65
    encounter
    0.63
    류
    0.60
    */].
    0.60
     employé
    0.60
     liên
    0.59
    Dixon
    0.59
    Activations Density 0.063%

    No Known Activations