© 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. 168737
    Prev
    Next
    INDEX
    Explanations

    positions and states

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

    peculiar institution

    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
    환
    0.52
    πλ
    0.47
    ورية
    0.43
    事件
    0.42
    今
    0.42
    NOW
    0.41
     환
    0.41
    ęcia
    0.40
    Yeni
    0.40
    yta
    0.40
    POSITIVE LOGITS
     hervorrag
    0.56
     UIS
    0.52
     achter
    0.51
    榱
    0.50
     Gefahr
    0.49
     Gubernur
    0.49
     ausgezeichnet
    0.49
     paljon
    0.49
     päiv
    0.49
     vadanti
    0.48
    Activations Density 0.001%

    No Known Activations