© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 100388
    Prev
    Next
    INDEX
    Explanations

    ImageNet classification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    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
    CSS
    0.43
     ("/
    0.38
     टीचर्स
    0.38
     tib
    0.36
    編成
    0.36
     असतो
    0.35
    えず
    0.35
     innoc
    0.34
    ("/",
    0.34
     tumors
    0.34
    POSITIVE LOGITS
    jada
    0.40
    jima
    0.39
    ុន
    0.38
     ಕರೆ
    0.38
     Honorary
    0.37
    iteits
    0.37
    ône
    0.37
     Diaz
    0.37
    Diam
    0.37
    дон
    0.36
    Activations Density 0.058%

    No Known Activations