© 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. 40-GEMMASCOPE-2-RES-262K
    7. 136662
    Prev
    Next
    INDEX
    Explanations

    code `.utils` or `.console`

    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
     negros
    0.36
     черно
    0.34
     subdomain
    0.34
    逑
    0.34
     слад
    0.34
     تم
    0.34
     बेह
    0.34
     Chalk
    0.33
    Джек
    0.33
    ૫
    0.33
    POSITIVE LOGITS
    গ্ধ
    0.47
     Bhagavato
    0.39
    ByMerging
    0.39
    并购
    0.39
    Leftrightarrow
    0.38
    ֿ
    0.37
    自行车
    0.37
    月の
    0.36
     lähe
    0.36
     Outside
    0.36
    Activations Density 0.006%

    No Known Activations