© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 56513
    Prev
    Next
    INDEX
    Explanations

    prepositions followed by nouns

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

    because they

    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
    Negative Logits
     compositions
    0.47
    ésil
    0.44
    ἠ
    0.42
    ipzig
    0.42
     Their
    0.41
     criticisms
    0.40
     Courtney
    0.40
     Careers
    0.40
     वैसा
    0.40
     mitigating
    0.40
    POSITIVE LOGITS
     Иван
    0.48
    자를
    0.46
    }\,
    0.45
    <0x0D>
    0.45
     oğ
    0.45
    단을
    0.45
    の上に
    0.45
    겠지만
    0.45
    SECONDARY
    0.45
     currentIndex
    0.44
    Activations Density 0.000%

    No Known Activations