© 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. 21338
    Prev
    Next
    INDEX
    Explanations

    file path errors

    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
     Direito
    -1.41
     appétit
    -1.38
     chèvre
    -1.37
    Ͳ
    -1.35
     עבודה
    -1.35
    𝕊
    -1.30
     chefe
    -1.30
     inova
    -1.27
     tieto
    -1.27
     peixe
    -1.27
    POSITIVE LOGITS
    Another
    1.34
     did
    1.23
    There
    1.18
     sagte
    1.18
     not
    1.18
     stimmt
    1.16
     never
    1.16
     [
    1.16
    Those
    1.16
     

    1.15
    Activations Density 0.026%

    No Known Activations