© 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. 159530
    Prev
    Next
    INDEX
    Explanations

    data processing and legal rights

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

    prepositional phrases and specific terms

    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
    s
    0.59
    in
    0.47
    scored
    0.46
    ey
    0.44
    sw
    0.44
    ch
    0.43
    resolved
    0.43
    shire
    0.41
     envisioned
    0.41
    isch
    0.40
    POSITIVE LOGITS
     السابع
    0.56
     بڑی
    0.54
     कीजिये
    0.53
     來
    0.53
     เตรียม
    0.52
     jedynie
    0.51
     وضعیت
    0.50
     negatif
    0.50
     abe
    0.50
    🚞
    0.50
    Activations Density 0.001%

    No Known Activations