© 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. 102395
    Prev
    Next
    INDEX
    Explanations

    at a rate

    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
     HIGHWAY
    -0.83
    ᄐ
    -0.82
    Doktor
    -0.82
    溝通
    -0.81
    波动
    -0.79
     Bernardo
    -0.79
    سجيل
    -0.78
    みます
    -0.78
    日発売
    -0.78
     transmitir
    -0.77
    POSITIVE LOGITS
     rate
    2.89
     rates
    2.30
    Rate
    2.09
    RATE
    2.03
    rate
    1.96
     Rate
    1.92
    rates
    1.74
     Rates
    1.74
    Rates
    1.73
     RATE
    1.73
    Activations Density 0.033%

    No Known Activations