© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 132748
    Prev
    Next
    INDEX
    Explanations

    questions and descriptions

    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
     doprav
    0.44
    posaż
    0.42
     sadrž
    0.39
     बरामद
    0.39
     ☑
    0.38
    न्नाथ
    0.38
     ዋ
    0.37
    ಕ್ಕಾಗಿ
    0.37
     čtyř
    0.37
    hegan
    0.37
    POSITIVE LOGITS
    优
    0.40
    尝试
    0.39
    壮
    0.37
     recon
    0.36
    ウル
    0.35
    墠
    0.35
    步
    0.35
    アルバ
    0.35
    вело
    0.35
    询问
    0.35
    Activations Density 0.000%

    No Known Activations