© 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. 86417
    Prev
    Next
    INDEX
    Explanations

    . ) €

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

    prepositions and conjunctions

    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
    ř
    0.49
     mangroves
    0.49
     Tonga
    0.47
    ayı
    0.44
    ė
    0.44
    书城
    0.44
    ny
    0.44
    to
    0.43
     ListTile
    0.43
    mère
    0.43
    POSITIVE LOGITS
     কিং
    0.44
    пион
    0.43
    ပ်
    0.43
     транспо
    0.43
    textwidth
    0.42
     সম্পাদক
    0.41
    ιος
    0.40
    ято
    0.40
    したが
    0.40
     ім
    0.39
    Activations Density 0.001%

    No Known Activations