© 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. 231205
    Prev
    Next
    INDEX
    Explanations

    prepositions or language connectors

    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
    ουν
    0.50
    appré
    0.47
    ремен
    0.47
    ופ
    0.46
    וק
    0.46
    춰
    0.45
    ів
    0.45
    ె
    0.44
    챔
    0.44
    리에
    0.44
    POSITIVE LOGITS
     sesu
    0.48
     mellom
    0.48
     Takes
    0.47
     bildet
    0.47
     antara
    0.46
     proses
    0.46
     Proses
    0.46
     Taken
    0.45
     tussen
    0.45
     handelt
    0.45
    Activations Density 0.001%

    No Known Activations