© 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. 118390
    Prev
    Next
    INDEX
    Explanations

    graphical properties or titles

    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
     Step
    -0.72
     Auft
    -0.72
     обстанов
    -0.71
     denna
    -0.69
     Classic
    -0.69
     ==
    -0.69
     quem
    -0.69
     parallels
    -0.69
    bés
    -0.69
     Boom
    -0.68
    POSITIVE LOGITS
     width
    1.16
     relief
    1.13
     highlight
    1.02
     Relief
    0.96
     bd
    0.95
     bg
    0.91
    highlight
    0.91
    width
    0.86
    Relief
    0.84
    Highlight
    0.84
    Activations Density 0.008%

    No Known Activations