© 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. 65637
    Prev
    Next
    INDEX
    Explanations

    Keith or Theodore followed by names

    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
    」　
    -1.48
     using
    -1.44
     in
    -1.42
     when
    -1.41
     to
    -1.33
     it
    -1.31
     because
    -1.30
     after
    -1.29
     Ș
    -1.28
     during
    -1.24
    POSITIVE LOGITS
     sechs
    1.48
     drei
    1.41
     gespielt
    1.41
     ","
    1.36
     três
    1.34
     sieben
    1.33
    钳
    1.30
    쫀
    1.27
     magnificent
    1.26
     mehreren
    1.26
    Activations Density 0.000%

    No Known Activations