© 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. 128803
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     in
    -2.64
     that
    -2.58
     if
    -2.44
     revital
    -2.36
     even
    -2.19
     before
    -2.17
     three
    -2.17
     while
    -2.17
     at
    -2.14
     for
    -2.13
    POSITIVE LOGITS
     delightfully
    2.58
     insanely
    2.56
     wacky
    2.48
     terrific
    2.47
     captivating
    2.45
     bizarre
    2.45
    訁
    2.42
     flamboyant
    2.41
     quintessential
    2.39
     VERY
    2.36
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.