© 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. 186539
    Prev
    Next
    INDEX
    Explanations

    prepositions followed by nouns

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

    listing alternatives

    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
    学科
    0.47
    .
    0.45
     doubleheader
    0.43
    ;
    0.42
    boat
    0.41
     nobles
    0.41
     FU
    0.40
     tabular
    0.40
     noble
    0.40
     plc
    0.40
    POSITIVE LOGITS
    스와
    0.50
    이나
    0.46
    하거나
    0.45
    ⦖
    0.44
     자신의
    0.43
     propia
    0.42
     আপনি
    0.42
    كيد
    0.42
    스키
    0.42
    自身の
    0.42
    Activations Density 0.001%

    No Known Activations