© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 13426
    Prev
    Next
    INDEX
    Explanations

    giving her his

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

    give me or tell me

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     เวลา
    0.45
     ตาย
    0.44
     ქვ
    0.44
     നിങ്ങൾക്ക്
    0.44
     bleaching
    0.42
    鱉
    0.42
     ช่วย
    0.41
     বিনামূল্যে
    0.41
     khuyến
    0.41
    獎
    0.41
    POSITIVE LOGITS
     svojim
    0.54
    简历
    0.52
     પોતાની
    0.50
     svoje
    0.50
     своим
    0.50
     اپنی
    0.47
     input
    0.47
     своих
    0.47
    了自己的
    0.47
    自己的
    0.46
    Activations Density 0.206%

    No Known Activations