© 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. 188814
    Prev
    Next
    INDEX
    Explanations

    contacting, returning, call, fines, Security

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

    storage devices

    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
     çizg
    0.46
     sajana
    0.45
     getchar
    0.45
     ocurr
    0.44
     Бы
    0.44
     angem
    0.44
    巻
    0.44
    ધુ
    0.43
     chromos
    0.43
    ajima
    0.43
    POSITIVE LOGITS
     Food
    0.48
    ี
    0.46
    สเตอร์
    0.46
    棻
    0.45
     लीड
    0.44
     ร่วม
    0.44
     Numerous
    0.43
     Hospice
    0.43
    是我们
    0.43
    辂
    0.42
    Activations Density 0.000%

    No Known Activations