© 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. 40-GEMMASCOPE-2-RES-262K
    7. 213462
    Prev
    Next
    INDEX
    Explanations

    demonstrate broader concepts

    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/layer_40_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
    ColorLegend
    0.41
    AttributeInfo
    0.41
    ]="
    0.39
    rond
    0.37
     inconsistencies
    0.37
    锺
    0.37
     répartition
    0.36
     достовер
    0.36
     कार्
    0.35
     immediately
    0.35
    POSITIVE LOGITS
    िने
    0.46
    🌅
    0.40
    лой
    0.39
    ಊ
    0.39
    ยาว
    0.38
     musicale
    0.37
     pli
    0.37
     tatto
    0.36
    hemer
    0.36
    🚵
    0.36
    Activations Density 0.001%

    No Known Activations