© 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. 54580
    Prev
    Next
    INDEX
    Explanations

    relative pronouns introducing descriptions

    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
     سکے۔
    0.49
     sebuah
    0.46
     тях
    0.45
    }$.
    0.45
     isang
    0.44
     แต
    0.43
     prawo
    0.42
     There
    0.42
    。
    0.42
     poseb
    0.41
    POSITIVE LOGITS
    ที่เรา
    0.74
    ที่คุณ
    0.67
     التي
    0.64
     الذي
    0.59
     которую
    0.55
     которые
    0.54
    ທີ່
    0.53
     التى
    0.52
     que
    0.52
     jakie
    0.51
    Activations Density 0.068%

    No Known Activations