© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 209932
    Prev
    Next
    INDEX
    Explanations

    note with directions

    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
     dimensions
    0.42
    ьев
    0.40
     dimensioni
    0.39
     accomplishment
    0.39
     ACHIEVEMENT
    0.39
    ̢
    0.39
    kov
    0.38
     dimens
    0.38
     achievement
    0.38
     adventure
    0.37
    POSITIVE LOGITS
     เกิด
    0.46
     落
    0.41
    算了
    0.40
     голосо
    0.40
     বঙ্গবন্ধুর
    0.39
    ленні
    0.38
     gehö
    0.38
     ಸಲ
    0.38
     شناخت
    0.38
    发展的
    0.37
    Activations Density 0.001%

    No Known Activations