© 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. 49761
    Prev
    Next
    INDEX
    Explanations

    LaTeX display alignment

    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
    qrstuvwxyz
    -0.81
    persky
    -0.79
    Siguiente
    -0.79
    勅
    -0.78
    govor
    -0.78
    COT
    -0.73
    戌
    -0.71
    bildēt
    -0.71
    Shalom
    -0.71
    يران
    -0.71
    POSITIVE LOGITS
    displaystyle
    1.28
     display
    1.26
    align
    1.15
    display
    1.15
    Display
    1.09
     aligned
    1.09
     align
    1.05
     matrix
    1.01
     Display
    0.96
     alignment
    0.94
    Activations Density 0.042%

    No Known Activations