© 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. 825
    Prev
    Next
    INDEX
    Explanations

    preposition "of" followed by a noun

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

    of descriptive 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
    ك
    0.37
    ка
    0.34
     како
    0.34
     ovog
    0.34
    <unused2197>
    0.34
    the
    0.34
     njegova
    0.33
     која
    0.33
     ако
    0.33
     এই
    0.33
    POSITIVE LOGITS
     products
    0.33
     experts
    0.31
    s
    0.30
    0.29
     well
    0.29
     materials
    0.29
     tools
    0.29
    Super
    0.29
     contractors
    0.29
     startups
    0.28
    Activations Density 0.552%

    No Known Activations