© 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. 77850
    Prev
    Next
    INDEX
    Explanations

    marketing, Jobs, campaign, learned

    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
    یف
    0.55
    मॉडल
    0.49
    ه‌ای
    0.47
    فت
    0.46
    ذی
    0.46
    étrico
    0.46
    ڑی
    0.45
    Ꞌ
    0.45
    ’’
    0.45
    با
    0.45
    POSITIVE LOGITS
    cription
    0.53
     не
    0.52
    _*
    0.52
    in
    0.51
     к
    0.51
     но
    0.51
     нового
    0.49
     harshly
    0.49
     стало
    0.46
    н
    0.46
    Activations Density 0.006%

    No Known Activations