© 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. 24866
    Prev
    Next
    INDEX
    Explanations

    plunger element

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

    Global Nature, Short documents, business impact

    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
    ਰ
    0.56
    発生
    0.54
    ра
    0.54
    летнего
    0.52
     BOOK
    0.52
    BOOK
    0.51
    ИК
    0.51
     महाभारत
    0.50
    簀
    0.49
    ਰਾ
    0.49
    POSITIVE LOGITS
    ذج
    0.44
     ot
    0.43
     والذي
    0.43
    varrho
    0.42
     তাড়
    0.41
    thati
    0.41
    Target
    0.41
    lande
    0.41
    peri
    0.41
     extrav
    0.40
    Activations Density 0.000%

    No Known Activations