© 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. 8814
    Prev
    Next
    INDEX
    Explanations

    sequential numbers and indices

    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
    Celebrating
    0.49
     кг
    0.49
    羢
    0.49
     मंत्रालय
    0.46
    кг
    0.45
    䆔
    0.45
    government
    0.44
    ávání
    0.44
    ný
    0.43
    攺
    0.43
    POSITIVE LOGITS
     another
    0.88
     दूसरा
    0.88
     fourth
    0.88
     second
    0.85
     third
    0.84
     two
    0.77
    3
    0.74
     zweiten
    0.73
    1
    0.71
     three
    0.71
    Activations Density 0.091%

    No Known Activations