© 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. 61314
    Prev
    Next
    INDEX
    Explanations

    penalties should, fantasy basketball, disorder sleep, red dog

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

    economic aspects and ownership

    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
     jerk
    0.50
     Terrible
    0.50
     움
    0.47
    tikzpicture
    0.47
     ईवी
    0.46
     অবিশ্বাস্য
    0.46
    trex
    0.45
     വരുന്ന
    0.45
     جیسے
    0.45
     ভিডি
    0.45
    POSITIVE LOGITS
    cció
    0.49
    ة
    0.48
    ва
    0.47
    色
    0.46
    riel
    0.45
    anium
    0.44
    مة
    0.43
    レット
    0.43
    煙
    0.43
    Ｂ
    0.40
    Activations Density 0.001%

    No Known Activations