© 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. 67285
    Prev
    Next
    INDEX
    Explanations

    Goku, Xiaolong, vs

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

    shonen anime fighting strength

    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
     কর্নেল
    0.52
     Komponenten
    0.45
    笄
    0.45
    ইডি
    0.45
    组件
    0.44
     служба
    0.43
    কল্যা
    0.43
     Hitchcock
    0.43
     GetComponent
    0.42
     пункт
    0.40
    POSITIVE LOGITS
    悟空
    0.65
     Goku
    0.61
    宇宙
    0.57
    🥋
    0.51
    quiao
    0.48
     आसमान
    0.48
     Vegeta
    0.48
     defeating
    0.47
     surpassed
    0.46
     brag
    0.46
    Activations Density 0.054%

    No Known Activations