© 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. 77696
    Prev
    Next
    INDEX
    Explanations

    speed manual, athletic trainers as part, a downpour, Schonfeld, busy Winter, encouraged to apply, along comes

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

    adding today

    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
    would
    0.47
    อ่อน
    0.46
    Introducing
    0.44
    住所
    0.44
    Att
    0.43
     I
    0.42
     Admit
    0.42
    ADDRESS
    0.42
    Attack
    0.41
     नम
    0.41
    POSITIVE LOGITS
    镂
    0.52
     因为
    0.49
    下滑
    0.47
    ilinear
    0.47
    婍
    0.46
     但是
    0.46
    ırlar
    0.45
     不需要
    0.45
    滗
    0.44
     星
    0.44
    Activations Density 0.000%

    No Known Activations