© 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. 112
    Prev
    Next
    INDEX
    Explanations

    names and capitalized words

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

    Sekt, Pika, Tribe, Delineate, Mophead, Pleurisy, Fantasies, Llama

    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
    6
    0.18
    8
    0.18
    7
    0.18
    4
    0.17
     troughs
    0.17
     splashes
    0.16
    0
    0.16
     attenuated
    0.16
     synced
    0.15
    2
    0.15
    POSITIVE LOGITS
    лла
    0.17
    Х
    0.16
    ia
    0.16
    М
    0.16
    i
    0.15
    وي
    0.15
     गौरतलब
    0.14
     foglie
    0.14
     Brooke
    0.14
    وس
    0.14
    Activations Density 1.092%

    No Known Activations