© 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. 80865
    Prev
    Next
    INDEX
    Explanations

    tickets, toward, purification, servant, voluntary, curious

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

    open, start, like, but

    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
    ract
    0.44
    ії
    0.44
    選
    0.43
     글로벌
    0.43
    提出
    0.42
    inputSelect
    0.42
    Declare
    0.41
    选择了
    0.41
    cs
    0.41
     نتیجه
    0.41
    POSITIVE LOGITS
     Vergangenheit
    0.53
     kaufen
    0.52
     erleben
    0.52
    اية
    0.52
    🖤
    0.50
     Existen
    0.48
     pól
    0.48
     Muy
    0.48
     clergyman
    0.48
     congén
    0.48
    Activations Density 0.000%

    No Known Activations