© 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. 26139
    Prev
    Next
    INDEX
    Explanations

    exceptions and errors

    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
     smör
    -1.27
     jego
    -1.23
    얌
    -1.23
     njego
    -1.23
     WIR
    -1.20
     staffel
    -1.18
     continually
    -1.17
     hecta
    -1.16
     sains
    -1.16
     purcha
    -1.14
    POSITIVE LOGITS
     this
    1.52
     what
    1.26
     classy
    1.24
     Getting
    1.22
     four
    1.20
     five
    1.19
     get
    1.17
    !
    1.16
     ruthless
    1.16
     getting
    1.16
    Activations Density 0.001%

    No Known Activations