© 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. 12484
    Prev
    Next
    INDEX
    Explanations

    letter A followed by punctuation

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

    first option in lists

    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
    টী
    0.42
    compile
    0.41
     отлич
    0.41
     Nor
    0.40
    name
    0.38
    {\"
    0.38
     {:.
    0.38
    categories
    0.37
    šie
    0.37
    uzu
    0.37
    POSITIVE LOGITS
    劵
    0.44
     választ
    0.41
    교
    0.40
     acumin
    0.39
     chimneys
    0.39
    راعظم
    0.38
     حلقات
    0.38
     धाम
    0.38
     recomendaciones
    0.38
     voglio
    0.38
    Activations Density 0.001%

    No Known Activations