© 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. 804
    Prev
    Next
    INDEX
    Explanations

    start of sentence phrases

    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
    2
    0.62
    3
    0.57
     planar
    0.55
     arrays
    0.53
     areal
    0.53
     processes
    0.52
     a
    0.51
     P
    0.51
     polygonal
    0.51
     absor
    0.50
    POSITIVE LOGITS
    ഘോഷ
    0.55
     zwycię
    0.54
     чыныгы
    0.54
    赢得
    0.54
     powiedział
    0.53
     estreia
    0.53
     ešte
    0.52
     jeudi
    0.51
     रैली
    0.51
    官员
    0.51
    Activations Density 0.396%

    No Known Activations