© 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. 33495
    Prev
    Next
    INDEX
    Explanations

    date and time formats

    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
     Expiration
    -0.77
    Carr
    -0.75
    жере
    -0.72
     Bite
    -0.71
    lq
    -0.70
    麦克
    -0.70
     Siren
    -0.70
     $\%
    -0.70
    ไหน
    -0.70
    Ln
    -0.70
    POSITIVE LOGITS
    olerance
    0.86
     चाहते
    0.85
    ERVIS
    0.82
     Spectrum
    0.81
    الر
    0.80
    gráfica
    0.80
    تص
    0.79
     Aoki
    0.77
     lenient
    0.77
    طب
    0.77
    Activations Density 0.023%

    No Known Activations