© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 38274
    Prev
    Next
    INDEX
    Explanations

    technical terms and identifiers

    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
    Warto
    -1.02
    Uwaga
    -1.00
     carico
    -0.89
    Dzięki
    -0.87
    未来的
    -0.86
     riserv
    -0.86
    Více
    -0.85
    Wię
    -0.84
     soluzione
    -0.83
    Rozmiar
    -0.83
    POSITIVE LOGITS
     “
    1.07
     "
    0.91
    länder
    0.87
     “[
    0.85
    tagged
    0.84
    VERB
    0.84
    орты
    0.83
     Fokus
    0.83
     "["
    0.82
     amethyst
    0.81
    Activations Density 0.003%

    No Known Activations