© 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. 22-GEMMASCOPE-RES-131K
    7. 15227
    Prev
    Next
    INDEX
    Explanations

    according to sources

    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_22/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
     and
    -1.67
     or
    -1.34
    unculus
    -1.16
     with
    -1.12
     Obviously
    -1.09
    nipeg
    -1.09
    észetes
    -1.07
     dítě
    -1.06
    。
    -1.05
     for
    -1.04
    POSITIVE LOGITS
     there
    1.87
     reason
    1.42
     existem
    1.35
     contenir
    1.35
    睒
    1.15
    鼍
    1.15
     kabel
    1.14
     :"
    1.12
     only
    1.11
    despite
    1.11
    Activations Density 0.020%

    No Known Activations