© 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. 15135
    Prev
    Next
    INDEX
    Explanations

    online or in stores

    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
     that
    -2.31
     which
    -1.52
     did
    -1.42
     
    -1.34
     -
    -1.27
     long
    -1.22
     methods
    -1.21
     repeatedly
    -1.19
     had
    -1.17
     develop
    -1.14
    POSITIVE LOGITS
     célè
    1.54
    𖧵
    1.34
    っそ
    1.31
    Innen
    1.30
    Aktual
    1.30
    Recept
    1.30
    tbx
    1.28
     siè
    1.27
     тільки
    1.23
    felizmente
    1.23
    Activations Density 0.034%

    No Known Activations