© 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. 242288
    Prev
    Next
    INDEX
    Explanations

    while, should, jumpers, she

    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
     yık
    0.52
    াট
    0.48
    гів
    0.46
     Quer
    0.43
     deixando
    0.42
     مشہور
    0.42
    骯
    0.41
     Maßnahmen
    0.40
     količ
    0.39
    这个人
    0.39
    POSITIVE LOGITS
    l
    0.56
     to
    0.52
    pel
    0.51
     seafood
    0.49
    petal
    0.49
    kates
    0.48
    pes
    0.48
     hospitalization
    0.48
     dentist
    0.47
    in
    0.47
    Activations Density 0.001%

    No Known Activations