© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 59212
    Prev
    Next
    INDEX
    Explanations

    Sprachgebrauch und Grammatik

    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
     tuh
    -1.69
    Schicken
    -1.51
    Beispiele
    -1.51
    Gründe
    -1.49
    Maß
    -1.45
    Polizei
    -1.45
     tiket
    -1.43
     cuci
    -1.43
     maksimal
    -1.43
    Vorteile
    -1.42
    POSITIVE LOGITS
     involucrados
    1.75
     auf
    1.50
     decorativos
    1.44
     mit
    1.40
     uphe
    1.38
     ráp
    1.37
     preparados
    1.35
    Mhm
    1.35
    Hü
    1.35
    cü
    1.34
    Activations Density 0.055%

    No Known Activations