© 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. 31-GEMMASCOPE-2-RES-262K
    7. 127785
    Prev
    Next
    INDEX
    Explanations

    book againinner and中 建立

    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
    า
    0.48
     Razer
    0.47
    വസ്ഥ
    0.47
    ื้อ
    0.46
     Velocity
    0.46
    学家
    0.46
     lepas
    0.45
    yers
    0.44
    leep
    0.43
    解除
    0.43
    POSITIVE LOGITS
    izhou
    0.48
    ầng
    0.47
    ỹ
    0.47
    फ्ते
    0.46
    ươi
    0.46
    ấm
    0.45
    }+
    0.45
    }+\
    0.44
    ຂໍ້ມ
    0.44
    ຜະລິດຕ
    0.44
    Activations Density 0.000%

    No Known Activations