© 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. 31-GEMMASCOPE-2-RES-262K
    7. 82764
    Prev
    Next
    INDEX
    Explanations

    form or process steps

    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
    ف
    0.52
    ))
    0.51
    مر
    0.50
    ));
    0.49
    ز
    0.49
     wanders
    0.47
    م
    0.46
    لم
    0.46
    ط
    0.45
    وف
    0.45
    POSITIVE LOGITS
     Lebesgue
    0.52
     Romantic
    0.52
     Linux
    0.51
     Tory
    0.50
     Conservative
    0.50
     Chrome
    0.50
     Labour
    0.49
     Comics
    0.49
     utilitarian
    0.48
    agre
    0.48
    Activations Density 0.000%

    No Known Activations