© 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. 78140
    Prev
    Next
    INDEX
    Explanations

    HTML label elements

    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
    Ẹ
    -0.81
     revés
    -0.80
    ädie
    -0.77
     Ook
    -0.75
     Grammar
    -0.75
    Puerto
    -0.73
     Ráp
    -0.72
    Ņ
    -0.72
    Истори
    -0.71
    btnClose
    -0.71
    POSITIVE LOGITS
    label
    1.48
     label
    1.41
     labels
    1.15
    labels
    1.04
    LABEL
    0.94
    setLabel
    0.93
     attached
    0.90
     LABEL
    0.88
     labelled
    0.85
     associated
    0.83
    Activations Density 0.010%

    No Known Activations