© 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-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 8351
    Prev
    Next
    INDEX
    Explanations

    Here's a breakdown

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_22_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
    andom
    0.92
    aino
    0.91
    iderman
    0.90
    aina
    0.89
     ಉ
    0.86
    ᐳ
    0.86
     दिखे
    0.84
    Purple
    0.81
    Ris
    0.80
    stehen
    0.80
    POSITIVE LOGITS
    缜
    1.14
    evice
    1.09
     لعبة
    0.98
    power
    0.97
     faculties
    0.97
    操作系统
    0.96
    遨
    0.95
     tricked
    0.94
     세포
    0.93
    skraft
    0.92
    Activations Density 0.139%

    No Known Activations