© 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. 64941
    Prev
    Next
    INDEX
    Explanations

    Robert Wynne, install with

    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
    mitglieder
    -1.13
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -1.11
    icles
    -1.07
    vidéo
    -1.06
     participer
    -1.05
     เว
    -1.05
     constater
    -1.03
    轳
    -1.02
     Somers
    -1.02
    และ
    -1.02
    POSITIVE LOGITS
     on
    1.53
     in
    1.36
     with
    1.21
     A
    1.17
     has
    1.16
     or
    1.16
     had
    1.13
     does
    1.09
     so
    1.07
     can
    1.07
    Activations Density 0.001%

    No Known Activations