© 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. 15086
    Prev
    Next
    INDEX
    Explanations

    prepositions followed by specific nouns

    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
     ON
    0.55
     SO
    0.52
     a
    0.52
     (\
    0.51
     +
    0.50
     the
    0.46
    SO
    0.46
     =
    0.46
     G
    0.45
     ||
    0.44
    POSITIVE LOGITS
    रोवर
    0.51
    mise
    0.47
    ),]),
    0.47
    szön
    0.47
    ಹ್
    0.46
    iędzy
    0.46
    investissement
    0.45
    民众
    0.45
    គ្រឿង
    0.45
    selectTable
    0.44
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.