© 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. 107992
    Prev
    Next
    INDEX
    Explanations

    Microsoft Copilot

    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
    ى
    0.46
    ضع
    0.44
    .
    0.40
     úspě
    0.40
     جیتنے
    0.40
    يمة
    0.39
     zerstört
    0.39
    icism
    0.39
     Require
    0.39
     عظ
    0.38
    POSITIVE LOGITS
    一緒
    0.48
    ４
    0.47
    മ്മ
    0.44
    ５
    0.44
    ላት
    0.43
    ﻤ
    0.43
    SCHEDULE
    0.42
    ப்பி
    0.42
    மர்
    0.41
     অন্যদের
    0.40
    Activations Density 0.011%

    No Known Activations