© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 10664
    Prev
    Next
    INDEX
    Explanations

    numbers containing 1

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

    988 US Canada 111 UK

    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_40_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
    tól
    0.47
    sman
    0.46
    hin
    0.44
    vip
    0.44
    텁
    0.44
    cers
    0.42
    tric
    0.42
    larından
    0.41
    nte
    0.41
     INTE
    0.41
    POSITIVE LOGITS
    П
    0.52
    Си
    0.47
    Π
    0.47
    Это
    0.46
    Über
    0.43
    צור
    0.43
    Время
    0.43
    আ
    0.43
    Ц
    0.43
     Jésus
    0.43
    Activations Density 0.082%

    No Known Activations