© 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. 76637
    Prev
    Next
    INDEX
    Explanations

    foreign language and medical terms

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

    age and description

    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
    Prairie
    0.50
     tailings
    0.46
    ਾਈ
    0.44
     প্রাই
    0.44
    υτό
    0.44
    ذ
    0.43
    ંદ્ર
    0.41
    代わりに
    0.41
     Archaeological
    0.41
    áu
    0.41
    POSITIVE LOGITS
    动
    0.43
     impot
    0.41
     esetben
    0.41
     испы
    0.41
     solvable
    0.41
     dexter
    0.40
     मरने
    0.40
     probl
    0.40
     trạng
    0.40
     annihilated
    0.40
    Activations Density 0.001%

    No Known Activations