© 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. 143067
    Prev
    Next
    INDEX
    Explanations

    saying "yeah" or "appreciate"

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

    grammar corrections

    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
    adhesive
    0.51
    ية
    0.50
    PRIVATE
    0.48
    chinese
    0.46
    DRIVER
    0.46
    CONSUM
    0.46
    coloured
    0.45
    ﺀ
    0.45
    uliert
    0.45
    ️
    0.44
    POSITIVE LOGITS
     Cristiano
    0.46
    瑗
    0.46
     nomin
    0.45
     arqué
    0.45
     Kyoto
    0.44
    นี
    0.44
     Lockwood
    0.44
     diversité
    0.44
    าลัย
    0.44
     Archive
    0.44
    Activations Density 0.001%

    No Known Activations