© 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. 76858
    Prev
    Next
    INDEX
    Explanations

    image files with .tif extension

    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
     this
    -1.17
     soothing
    -1.16
     took
    -1.15
     from
    -1.10
    ньому
    -1.05
     unbelievable
    -1.04
     before
    -1.04
     both
    -1.02
     trying
    -0.98
     शुर
    -0.96
    POSITIVE LOGITS
     เช
    1.37
     Dinas
    1.13
     decidedly
    1.05
     rokok
    1.05
     בְּ
    1.05
     remarkably
    1.04
     VERY
    1.04
     trám
    1.03
     olymp
    1.02
     strikingly
    1.02
    Activations Density 0.038%

    No Known Activations