© 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. 41-GEMMASCOPE-2-RES-262K
    7. 103115
    Prev
    Next
    INDEX
    Explanations

    formula functionality

    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_all/layer_41_width_262k_l0_big
    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
    菘
    0.44
    teborg
    0.40
     اپنا
    0.40
     atof
    0.40
     хто
    0.38
     প্রসঙ্গ
    0.37
    тическая
    0.37
     energetics
    0.37
    萵
    0.37
     JavaBeans
    0.36
    POSITIVE LOGITS
     ért
    0.41
    秀
    0.40
     Consider
    0.39
     dangerously
    0.38
     mostró
    0.38
     considere
    0.38
     mischiev
    0.37
    jiv
    0.37
     significantly
    0.37
    value
    0.36
    Activations Density 0.000%

    No Known Activations