© 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. 29-GEMMASCOPE-2-RES-16K
    7. 3466
    Prev
    Next
    INDEX
    Explanations

    to generate

    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_29_width_16k_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
     પ્રિય
    0.76
    পথ
    0.63
    crum
    0.62
    侘
    0.62
    <unused2179>
    0.60
     toNumber
    0.60
    طانیہ
    0.59
    स्वी
    0.59
     প্রতিষ্ঠার
    0.58
    鄙
    0.58
    POSITIVE LOGITS
     Generate
    4.70
     generate
    4.68
    Generate
    4.62
     generated
    4.58
     generation
    4.55
    generate
    4.50
     generating
    4.49
     Generating
    4.35
    生成
    4.35
     Generation
    4.34
    Activations Density 1.825%

    No Known Activations