© 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. 45103
    Prev
    Next
    INDEX
    Explanations

    group theory notation

    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
     archivos
    0.44
    𝚁
    0.42
    iliki
    0.42
     GET
    0.40
     procl
    0.40
     gazet
    0.39
     arr
    0.38
    arq
    0.38
     fichiers
    0.37
    خت
    0.37
    POSITIVE LOGITS
     ομά
    0.48
     Sutton
    0.45
    +(-
    0.44
     ομάδα
    0.44
     naturalmente
    0.43
    PIPE
    0.42
     ভঙ্গ
    0.42
    柔軟
    0.42
    SubType
    0.41
     hỗn
    0.41
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.