© 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. 172521
    Prev
    Next
    INDEX
    Explanations

    interesting article

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

    initial information retrieval

    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
     ولي
    0.57
     活动
    0.54
     安装
    0.54
     הש
    0.52
     赵
    0.52
     TERM
    0.51
     साल
    0.50
     Zusammenhang
    0.50
    ឍ
    0.49
     oraz
    0.49
    POSITIVE LOGITS
    !)
    0.49
    ä
    0.46
    )~
    0.46
    !).
    0.44
    ากร
    0.43
    ~)
    0.43
    alt
    0.42
    ae
    0.42
    じる
    0.42
    iflower
    0.42
    Activations Density 0.001%

    No Known Activations