© 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. 198013
    Prev
    Next
    INDEX
    Explanations

    tag me, bottles, win

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

    federal taxes

    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
     Tai
    0.47
     unilateral
    0.46
     century
    0.42
     tai
    0.42
     преж
    0.42
    antec
    0.42
     syndrome
    0.42
    巒
    0.41
    mixing
    0.40
    탰
    0.40
    POSITIVE LOGITS
     হত্যাকাণ্ড
    0.55
     পৃথিবী
    0.54
     erzählt
    0.52
    দ্দা
    0.50
     পৃথিবীতে
    0.49
     ایالات
    0.49
     পাকিস্তানে
    0.48
     erzählen
    0.48
     চট্টগ্রামের
    0.47
     మరియు
    0.46
    Activations Density 0.006%

    No Known Activations