© 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. 222173
    Prev
    Next
    INDEX
    Explanations

    Plasma Technology

    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
     pelea
    0.43
     वाणिज्य
    0.42
     दिक्कत
    0.41
    frameN
    0.41
    wheel
    0.39
    ']=$
    0.39
     peering
    0.39
    놋
    0.39
     acorns
    0.39
    isTrack
    0.39
    POSITIVE LOGITS
     Views
    0.38
    术
    0.38
    ذي
    0.36
     inherit
    0.36
    Volumes
    0.35
     Valves
    0.34
     possess
    0.34
    খ্য
    0.34
    أة
    0.34
    ovati
    0.33
    Activations Density 0.016%

    No Known Activations