© 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. 84302
    Prev
    Next
    INDEX
    Explanations

    critical choice

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

    questions people ask

    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
    يت
    0.61
    น
    0.48
    دد
    0.48
     auxquels
    0.45
    chten
    0.44
     titulares
    0.44
    به
    0.44
    نه
    0.44
    épend
    0.44
    ن
    0.43
    POSITIVE LOGITS
     ৪০০
    0.59
    ᱗
    0.55
     পূরণ
    0.49
    櫸
    0.49
     fragmentary
    0.48
     реки
    0.47
    ഭം
    0.47
     sadrž
    0.46
    +"|
    0.46
     перемо
    0.46
    Activations Density 0.000%

    No Known Activations