© 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. 128769
    Prev
    Next
    INDEX
    Explanations

    citations markers

    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
     in
    -3.13
     to
    -2.59
     is
    -2.56
     or
    -2.50
     on
    -2.50
     A
    -2.36
     for
    -2.34
     Some
    -2.06
     as
    -2.05
     In
    -2.02
    POSITIVE LOGITS
     aussit
    2.33
     abiye
    2.27
     générer
    2.22
     jari
    2.22
     créer
    2.20
     occuper
    2.20
     glisser
    2.20
    厛
    2.20
     provoquer
    2.19
     keramik
    2.17
    Activations Density 0.028%

    No Known Activations