© 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. 253989
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     be
    0.57
    :
    0.55
     einer
    0.52
     ór
    0.52
     been
    0.50
     THAN
    0.50
    and
    0.50
     CONNECT
    0.49
     can
    0.49
     LAYER
    0.49
    POSITIVE LOGITS
    মূ
    0.52
    मला
    0.49
    쐞
    0.48
     বিদ্যালয়
    0.46
    циям
    0.45
    इयों
    0.44
    اداسی
    0.44
     विद्यालय
    0.43
    ኞ
    0.43
    鼕
    0.43
    Activations Density 0.001%

    No Known Activations