© 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. 22451
    Prev
    Next
    INDEX
    Explanations

    specific entities followed by common words

    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
     aislados
    -1.56
     chré
    -1.41
    
    -1.39
    ствен
    -1.38
     Mitgliedern
    -1.37
    wählen
    -1.36
    колко
    -1.34
     coloridos
    -1.34
     üzerine
    -1.32
     mindig
    -1.31
    POSITIVE LOGITS
     are
    1.65
     eter
    1.27
     collaborating
    1.23
     كافة
    1.20
    leq
    1.17
    暧
    1.16
     vehe
    1.15
    浒
    1.15
    Y
    1.13
    película
    1.12
    Activations Density 0.008%

    No Known Activations