© 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. 198164
    Prev
    Next
    INDEX
    Explanations

    organs, medication, cap

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

    body, medical, materials, following

    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
    湫
    0.47
    irs
    0.46
    ётся
    0.46
    okine
    0.46
    oling
    0.46
    梸
    0.46
     منظر
    0.45
     ხელისუფ
    0.43
    िक्ट
    0.43
    irth
    0.43
    POSITIVE LOGITS
    InSection
    0.55
     coldly
    0.52
    Alle
    0.51
     в
    0.49
    Дру
    0.48
     in
    0.48
    Seine
    0.48
     can
    0.47
    ’
    0.46
     ч
    0.46
    Activations Density 0.000%

    No Known Activations