© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 985
    Prev
    Next
    INDEX
    Explanations

    Slovenian, Meta

    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_34/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
     afterward
    -0.83
     femenina
    -0.81
    šė
    -0.74
     Gesund
    -0.72
     Läs
    -0.71
     yli
    -0.70
     ايران
    -0.70
    }")]
    -0.69
     specifics
    -0.69
     với
    -0.68
    POSITIVE LOGITS
    SPARENT
    0.85
    Père
    0.82
    Alger
    0.77
    Opere
    0.76
     Colossus
    0.76
     documents
    0.73
     ſer
    0.73
    Premier
    0.72
     Inca
    0.72
    Coordenadas
    0.71
    Activations Density 0.010%

    No Known Activations