© 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. 34-GEMMASCOPE-RES-131K
    7. 31701
    Prev
    Next
    INDEX
    Explanations

    HTML meta tags and code comments

    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
    க்
    -0.79
    日閲覧
    -0.78
     gleich
    -0.77
     yeast
    -0.76
    aurora
    -0.75
     then
    -0.73
    mole
    -0.73
    portar
    -0.73
    Proc
    -0.73
    |=
    -0.73
    POSITIVE LOGITS
     bundles
    0.79
    bundles
    0.78
    きます
    0.77
    oweit
    0.75
    Producción
    0.75
     fej
    0.74
     Informasi
    0.74
    mulher
    0.73
     acercar
    0.73
     Betrach
    0.72
    Activations Density 0.002%

    No Known Activations