© 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-65K
    7. 31270
    Prev
    Next
    INDEX
    Explanations

    authorities, help, and evolutionary computation

    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_65k_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
    ب
    0.51
    ح
    0.50
    거
    0.47
    স
    0.47
    为了
    0.45
    Holly
    0.45
    Mon
    0.45
    平
    0.44
    ਵ
    0.44
    ق
    0.44
    POSITIVE LOGITS
     eignet
    0.52
     話
    0.51
     úlo
    0.50
     تعريف
    0.50
     ഇടപെ
    0.48
     ใด
    0.48
     }}(\
    0.48
     학습
    0.46
     uczni
    0.46
     നിങ്ങളുടെ
    0.46
    Activations Density 0.002%

    No Known Activations