© 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. 2645
    Prev
    Next
    INDEX
    Explanations

    mathematical and specialized notation

    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
    fml
    -0.82
    ICALLY
    -0.79
     Iowa
    -0.76
    thumbnails
    -0.75
    AILS
    -0.75
    veda
    -0.74
     Associates
    -0.73
    %!
    -0.73
    ゆっくり
    -0.73
     manchmal
    -0.73
    POSITIVE LOGITS
    Surprised
    0.81
    Terrible
    0.75
    Coucou
    0.75
    Blame
    0.75
    witter
    0.73
     Gratis
    0.73
    ❐
    0.72
     notare
    0.72
    Parfait
    0.72
    用意
    0.71
    Activations Density 0.000%

    No Known Activations