© 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. 64101
    Prev
    Next
    INDEX
    Explanations

    preposition or determiner following common words

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

    prepositions followed by context words

    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
     توسیع
    0.53
    invariant
    0.50
    သည်။
    0.49
     रामानंद
    0.47
     Orsay
    0.45
    ₀
    0.45
     ribosomes
    0.45
    бліоте
    0.44
    Pharmaceutical
    0.44
    algebras
    0.43
    POSITIVE LOGITS
    })$;
    0.46
     мах
    0.45
     triển
    0.44
     meliputi
    0.43
    מ
    0.43
     atualizar
    0.42
     сі
    0.42
    })=\
    0.42
    SAMPLE
    0.42
     kics
    0.41
    Activations Density 0.000%

    No Known Activations