© 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. 40-GEMMASCOPE-2-RES-16K
    7. 11850
    Prev
    Next
    INDEX
    Explanations

    names ending in "-en" or "-er"

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

    Elden Ring, Lumen, Wokeness, Golden, Broken

    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
    d
    0.54
    률
    0.48
    たり
    0.48
    と思います
    0.47
    観
    0.47
    ten
    0.47
    촌
    0.46
    啉
    0.46
    ta
    0.45
    ínio
    0.44
    POSITIVE LOGITS
    omics
    0.69
    chyma
    0.66
    ‍♂️
    0.66
    vironment
    0.64
     گے
    0.63
    berger
    0.62
    autes
    0.61
    ‍♂
    0.61
    ‍♀️
    0.60
    egger
    0.59
    Activations Density 0.975%

    No Known Activations