© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 14201
    Prev
    Next
    INDEX
    Explanations

    copyright notice and license

    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_10/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
     duvar
    -1.60
     fün
    -1.57
     lasts
    -1.52
    investissement
    -1.51
     знают
    -1.41
     приняли
    -1.41
    número
    -1.41
     hindered
    -1.40
     beş
    -1.40
    eater
    -1.39
    POSITIVE LOGITS
     millioner
    1.71
    with
    1.71
     آنها
    1.66
     brune
    1.66
     With
    1.65
     and
    1.60
     They
    1.59
    end
    1.59
     dengan
    1.59
     sentral
    1.58
    Activations Density 0.002%

    No Known Activations