© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 36300
    Prev
    Next
    INDEX
    Explanations

    SVG path commands containing C

    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
    face
    0.38
    lwjglVersion
    0.38
    ienia
    0.37
     प्रोत्साहित
    0.37
     forState
    0.37
    详
    0.37
     lezen
    0.37
     машинасы
    0.37
    NESOTA
    0.37
     puk
    0.37
    POSITIVE LOGITS
     innermost
    0.40
     เดียว
    0.37
     curvature
    0.37
     ਇ
    0.36
     Fili
    0.36
    Ж
    0.36
     Kur
    0.36
     Belle
    0.36
    mberg
    0.36
     Balashov
    0.35
    Activations Density 0.004%

    No Known Activations