© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 14523
    Prev
    Next
    INDEX
    Explanations

    time ago

    np_acts-logits-general · gemini-2.5-flash-lite

    concepts, attributes, or terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     reprim
    0.48
     ulcer
    0.45
     rotten
    0.45
    س
    0.44
     مرور
    0.44
     sorption
    0.43
     shirt
    0.43
    THRESHOLD
    0.43
     circuit
    0.43
     sky
    0.42
    POSITIVE LOGITS
    ವನ್ನು
    0.54
     එව
    0.53
    ியுள்ளது
    0.49
    ensure
    0.49
     Ер
    0.49
    untos
    0.48
    み
    0.47
     Suresh
    0.46
    fors
    0.46
     ಕ್ಯಾ
    0.46
    Activations Density 0.001%

    No Known Activations