© 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. 22350
    Prev
    Next
    INDEX
    Explanations

    recipient governments

    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
    这
    0.52
    utzerklärung
    0.49
    训练
    0.46
    啻
    0.46
    لق
    0.46
    ности
    0.45
    召开
    0.45
    c
    0.44
    നങ്ങൾ
    0.44
    装
    0.44
    POSITIVE LOGITS
    বস্ত
    0.47
     berupa
    0.47
     tund
    0.45
    টির
    0.43
     targets
    0.42
     consisting
    0.41
    ურნ
    0.41
     composed
    0.41
     সাব
    0.41
     itens
    0.41
    Activations Density 0.108%

    No Known Activations