© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-262K
    4. 2022
    Prev
    Next
    INDEX
    Explanations

    finding specific answers or code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     faptul
    1.16
    rolysis
    1.15
     copa
    1.11
     смеси
    1.06
     surgi
    1.05
     goalie
    1.05
    홉
    1.04
    ツール
    1.03
     बच्‍
    1.03
     collar
    1.02
    POSITIVE LOGITS
    دت
    1.09
    ண்முக
    1.03
    $^{-
    0.93
    scales
    0.91
    دة
    0.89
    ers
    0.89
    ت
    0.88
    Azure
    0.88
    igans
    0.87
    น่า
    0.86
    Activations Density 0.000%

    No Known Activations