© 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. 203985
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns and verb endings

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

    Average or normal

    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
    Sl
    0.51
    mc
    0.50
     on
    0.50
    Details
    0.49
    метка
    0.48
    MA
    0.47
    MC
    0.47
    &#
    0.47
    AGA
    0.46
     occupa
    0.46
    POSITIVE LOGITS
    随时
    0.54
     cantidades
    0.45
    нтип
    0.44
    اتب
    0.44
    ilerini
    0.43
     ومل
    0.43
    ➌
    0.43
    ड्स
    0.42
     déplacer
    0.42
    뒹
    0.42
    Activations Density 0.002%

    No Known Activations