© 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. 23239
    Prev
    Next
    INDEX
    Explanations

    son Mark, kid making, SD card

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

    explaining specifics

    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
    <start_of_image>
    0.38
     poiché
    0.29
     ponieważ
    0.29
     فونبیٹ
    0.28
     سلاټ
    0.25
     زمانی
    0.25
     ancak
    0.25
    จึง
    0.25
    </h2>
    0.25
     tehát
    0.25
    POSITIVE LOGITS
     很
    0.31
     చాలా
    0.31
     ד
    0.30
     वगैर
    0.30
    珩
    0.28
     ಬಹಳ
    0.28
     mấy
    0.28
     제대로
    0.28
     ህ
    0.27
    很好的
    0.27
    Activations Density 0.027%

    No Known Activations