© 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. 188460
    Prev
    Next
    INDEX
    Explanations

    begin review, movements totaled, vision checked, popular demand

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

    connection okay, two items, not storing

    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
    तलब
    0.47
     स्टूडेंट्स
    0.46
    ланган
    0.45
    ط
    0.45
    é
    0.44
    墅
    0.44
    ᾧ
    0.44
     Erect
    0.44
     priests
    0.43
     landlords
    0.43
    POSITIVE LOGITS
    )$.
    0.52
    )).
    0.51
     nij
    0.47
    )。
    0.47
     reducción
    0.46
    yty
    0.45
     没有
    0.45
     نی
    0.45
     ترکی
    0.45
     повы
    0.44
    Activations Density 0.002%

    No Known Activations