© 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. 246394
    Prev
    Next
    INDEX
    Explanations

    various languages and grammatical structures

    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
    Account
    0.45
     പഞ്ച
    0.45
    iant
    0.44
     Account
    0.42
    軍
    0.42
     form
    0.41
     الأولى
    0.41
    ｺ
    0.41
    KIN
    0.41
     單
    0.41
    POSITIVE LOGITS
    었다
    0.52
    ánico
    0.50
    تاریخ
    0.50
     aquilo
    0.48
    epoca
    0.48
     inseg
    0.47
     czas
    0.47
     ciem
    0.47
     molé
    0.46
     roca
    0.46
    Activations Density 0.001%

    No Known Activations