© 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. 102292
    Prev
    Next
    INDEX
    Explanations

    may be or may have

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

    levels and hierarchies

    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
     earmarked
    0.48
     son
    0.45
     genu
    0.45
     Khanna
    0.45
     }}$
    0.45
    M
    0.45
     큰
    0.44
     сон
    0.43
    KM
    0.43
    PC
    0.42
    POSITIVE LOGITS
    kait
    0.57
    верса
    0.52
    বরা
    0.52
    ложен
    0.51
     între
    0.51
    هل
    0.50
    ación
    0.49
    蜢
    0.49
    eliest
    0.49
    به
    0.48
    Activations Density 0.001%

    No Known Activations