© 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. 129054
    Prev
    Next
    INDEX
    Explanations

    collectible items and art

    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
    珦
    -1.37
    maillot
    -1.30
    miniature
    -1.28
     realmente
    -1.27
     planific
    -1.23
     necessária
    -1.23
     to
    -1.23
     dreadful
    -1.22
     douane
    -1.21
    boite
    -1.19
    POSITIVE LOGITS
     but
    1.43
     what
    1.30
    AZIONI
    1.25
     isolato
    1.20
    年には
    1.19
    Even
    1.18
     because
    1.16
    AH
    1.13
    بح
    1.13
     an
    1.13
    Activations Density 0.056%

    No Known Activations