© 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. 31-GEMMASCOPE-2-RES-262K
    7. 4848
    Prev
    Next
    INDEX
    Explanations

    variety of, one of

    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_31_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
     organism
    0.41
     worms
    0.39
     deformed
    0.39
    Ultr
    0.39
     claws
    0.37
     (
    0.35
     PHY
    0.35
     contents
    0.35
     fusion
    0.35
     dielectric
    0.35
    POSITIVE LOGITS
     अमाउंट
    0.54
     그러면은
    0.49
    ডাক্ট
    0.48
     ahorita
    0.48
     बेसिकली
    0.47
     एक्सपेक्ट
    0.46
     परसेंटेज
    0.45
    🫣
    0.45
    сторінку
    0.45
     Ouais
    0.45
    Activations Density 0.001%

    No Known Activations