© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 90553
    Prev
    Next
    INDEX
    Explanations

    challenge your senses

    np_acts-logits-general · gemini-2.5-flash-lite

    rhetorically emphasized or high-salience words that signal intensity, importance, or narrative/expository transitions.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    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
     शैक्षणिक
    0.48
     ನೀರಿನ
    0.47
    
    0.47
     Unterricht
    0.46
    MathMarks
    0.46
     Woodland
    0.46
     ł
    0.45
     Rubens
    0.45
    দ্যাল
    0.44
    urangan
    0.44
    POSITIVE LOGITS
    fug
    0.43
    ير
    0.40
     unbelievable
    0.40
    parseDouble
    0.39
    래
    0.39
    Invoice
    0.38
    庞
    0.38
    download
    0.38
    вість
    0.38
    StarService
    0.38
    Activations Density 0.004%

    No Known Activations