© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 33122
    Prev
    Next
    INDEX
    Explanations

    prepositions of movement and relation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ಿ
    0.45
    中学
    0.41
    '><
    0.38
    で見
    0.38
    鉭
    0.37
     문제입니다
    0.37
     আপাত
    0.37
     IncludeField
    0.37
    পির
    0.36
    暉
    0.36
    POSITIVE LOGITS
     onto
    1.02
     across
    1.02
     into
    1.01
    into
    0.92
    across
    0.89
    ไปยัง
    0.80
     outwards
    0.79
    Into
    0.76
     between
    0.75
    Across
    0.74
    Activations Density 0.003%

    No Known Activations