© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 4556
    Prev
    Next
    INDEX
    Explanations

    textbooks and chapters

    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
     formée
    1.11
    핌
    0.98
     माफी
    0.97
    ᶜ
    0.96
     prit
    0.95
    蔥
    0.94
     policía
    0.91
     صلى
    0.90
    Fonts
    0.90
     échelle
    0.90
    POSITIVE LOGITS
    chapters
    1.04
     chapters
    1.03
     Kapitel
    0.89
     Chapters
    0.87
    ו
    0.87
    𝘸
    0.85
     chapter
    0.84
     phantom
    0.83
    স
    0.83
     costing
    0.83
    Activations Density 0.006%

    No Known Activations