© 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. 31-GEMMASCOPE-2-RES-262K
    7. 125540
    Prev
    Next
    INDEX
    Explanations

    and the

    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_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
     হাসপাত
    0.40
    ▄
    0.38
     yd
    0.38
     polos
    0.38
     estremamente
    0.38
    لوار
    0.37
    ᆹ
    0.36
     empresa
    0.36
     pinched
    0.35
    Concini
    0.35
    POSITIVE LOGITS
     특별
    0.41
    ม
    0.39
    ref
    0.39
     出
    0.38
    ieszcz
    0.38
     সফল
    0.38
     cuộc
    0.37
     ரசிகர்கள்
    0.37
     মধ্যে
    0.37
    뚝
    0.37
    Activations Density 0.002%

    No Known Activations