© 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. 113811
    Prev
    Next
    INDEX
    Explanations

    identifies "this" followed by a concept

    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
     However
    -1.38
    衎
    -1.34
     [
    -1.30
     increased
    -1.21
     their
    -1.20
    ࣭
    -1.20
     those
    -1.20
     each
    -1.19
    Those
    -1.18
     when
    -1.16
    POSITIVE LOGITS
     reparación
    1.31
     protéger
    1.25
    Цент
    1.15
    
    1.15
     créer
    1.10
     yder
    1.09
    آیا
    1.09
     ajouter
    1.06
    Ј
    1.06
     voitures
    1.05
    Activations Density 0.132%

    No Known Activations