© 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. 8424
    Prev
    Next
    INDEX
    Explanations

    possessive\/genitive marker

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

    prepositions in many languages

    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
    ূলে
    0.41
    أي
    0.40
    ้
    0.38
     кількість
    0.38
    雱
    0.37
    да
    0.37
    ần
    0.37
    في
    0.37
    ඈ
    0.37
     גם
    0.37
    POSITIVE LOGITS
     of
    0.50
     της
    0.50
     بتاعت
    0.49
     của
    0.48
     của
    0.48
     των
    0.47
     tejto
    0.45
     ochrony
    0.44
     tohoto
    0.43
     działalności
    0.43
    Activations Density 0.123%

    No Known Activations