© 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. 222508
    Prev
    Next
    INDEX
    Explanations

    publicly perform

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

    linking words/punctuation

    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
    兽
    0.52
    긍
    0.49
     služ
    0.45
    伟
    0.45
    谁
    0.44
    شي
    0.44
     ellát
    0.44
    诊
    0.43
    明显
    0.43
    尘
    0.43
    POSITIVE LOGITS
    ali
    0.57
    allow
    0.56
    on
    0.55
    con
    0.55
    are
    0.54
    other
    0.54
    can
    0.54
    allowed
    0.53
    al
    0.52
    asiti
    0.52
    Activations Density 0.001%

    No Known Activations