© 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. 109214
    Prev
    Next
    INDEX
    Explanations

    code snippets in various languages

    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
    allaitement
    0.45
     아마
    0.41
     veden
    0.40
     Ă
    0.40
     കൂടുതൽ
    0.38
     Incluso
    0.36
     நடத்திய
    0.35
     নেতৃত্ব
    0.35
     ನೆಲ
    0.34
     Далее
    0.34
    POSITIVE LOGITS
     helper
    0.36
     possibilidades
    0.34
    化
    0.34
    CO
    0.33
    ArgumentParser
    0.33
    소
    0.33
    <0xB7>
    0.33
    ento
    0.33
     geométricas
    0.33
    వం
    0.32
    Activations Density 0.026%

    No Known Activations