© 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. 99393
    Prev
    Next
    INDEX
    Explanations

    possession and obligation

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

    specific project achievement

    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
    Перед
    0.57
    vané
    0.55
    섞
    0.55
     nhằm
    0.52
     связанные
    0.52
    بی
    0.50
     Перед
    0.49
     альбо
    0.49
    ৫৮
    0.49
    ających
    0.48
    POSITIVE LOGITS
     monolith
    0.49
    臧
    0.46
     Dz
    0.46
     Bek
    0.45
     boh
    0.45
     Kaufmann
    0.45
    hold
    0.44
     Pavlov
    0.43
     Villa
    0.43
     Torre
    0.43
    Activations Density 0.001%

    No Known Activations