© 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. 22-GEMMASCOPE-RES-131K
    4. 130614
    Prev
    Next
    INDEX
    Explanations

    SQL column names

    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_22/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
    国民
    -0.82
    ینت
    -0.81
    ))
    -0.76
    érez
    -0.73
    メッセージ
    -0.73
    Beskrivning
    -0.73
     Intensi
    -0.72
     instala
    -0.70
     conversation
    -0.70
     però
    -0.69
    POSITIVE LOGITS
    ఎ
    0.92
     enquanto
    0.89
     Juegos
    0.85
    конец
    0.80
    synchronize
    0.80
     FIR
    0.79
    yní
    0.78
    の一部
    0.78
    quisar
    0.77
    Ho
    0.77
    Activations Density 0.117%

    No Known Activations