© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 100714
    Prev
    Next
    INDEX
    Explanations

    formed through a reality show

    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_262k_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
     sleepers
    0.43
     Lankan
    0.43
     safest
    0.42
    否
    0.40
     needlessly
    0.40
    あらゆる
    0.40
     Evet
    0.39
     бекер
    0.39
     blanket
    0.39
    etzte
    0.39
    POSITIVE LOGITS
    viso
    0.42
     فلسطینی
    0.41
    munition
    0.41
    ס
    0.41
     উপস
    0.41
    Histogram
    0.41
    histogram
    0.40
     FLEX
    0.40
    britannien
    0.40
    谚
    0.40
    Activations Density 0.001%

    No Known Activations