© 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. 41-GEMMASCOPE-2-RES-262K
    7. 32977
    Prev
    Next
    INDEX
    Explanations

    moving up, down, or diagonally

    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
     പ്രത്യേ
    0.44
    мії
    0.42
    ഭാഗ
    0.38
     infine
    0.37
    這次
    0.36
     시간에는
    0.36
    بة
    0.35
    國
    0.35
    城堡
    0.34
     întâm
    0.34
    POSITIVE LOGITS
     two
    0.87
    two
    0.85
    一步
    0.84
     step
    0.82
     två
    0.79
     deux
    0.79
     one
    0.78
     दोन
    0.77
    一级
    0.76
     няколко
    0.75
    Activations Density 0.004%

    No Known Activations