© 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. 10-GEMMASCOPE-RES-131K
    7. 40075
    Prev
    Next
    INDEX
    Explanations

    structures and systems

    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_10/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
     '/';
    -1.38
     specif
    -1.38
     curent
    -1.36
    乄
    -1.34
     OBITUARY
    -1.34
     ISLAND
    -1.34
     étages
    -1.33
     ooo
    -1.33
     permitan
    -1.32
    УДК
    -1.31
    POSITIVE LOGITS
     with
    2.41
     in
    1.96
     these
    1.95
     These
    1.75
    These
    1.66
     two
    1.58
     With
    1.55
     for
    1.55
     Two
    1.51
     is
    1.49
    Activations Density 0.780%

    No Known Activations