© 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. 206324
    Prev
    Next
    INDEX
    Explanations

    foolish to, transaction., spots are, much of, with an

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

    Attention is All You Need

    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
     BOTH
    0.47
    theorem
    0.46
    Meesho
    0.46
    Avoid
    0.46
     rectangles
    0.45
     STUDIES
    0.44
     migliore
    0.44
    ੁ
    0.43
     condizione
    0.43
     гле
    0.42
    POSITIVE LOGITS
     Faz
    0.46
     Gillespie
    0.41
    لة
    0.40
    妘
    0.40
     Lai
    0.40
    竟然
    0.39
     அழைத்து
    0.39
     də
    0.39
     Chast
    0.39
     రాజు
    0.39
    Activations Density 0.000%

    No Known Activations