© 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. 40196
    Prev
    Next
    INDEX
    Explanations

    common prepositions or articles

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

    chess squares, lists, boards

    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
     rétréc
    0.48
     correttamente
    0.48
     বিষয়টি
    0.47
    ামুটি
    0.46
    ༤
    0.46
     квіт
    0.45
     avancé
    0.45
     точки
    0.44
     correctement
    0.44
     convexe
    0.44
    POSITIVE LOGITS
     is
    0.55
    v
    0.49
     \
    0.49
     (
    0.47
    ग
    0.47
    ab
    0.46
     WH
    0.46
     nesses
    0.45
     names
    0.45
     trouble
    0.44
    Activations Density 0.000%

    No Known Activations