© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 93378
    Prev
    Next
    INDEX
    Explanations

    historical periods and structures

    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
    パク
    0.52
     می
    0.51
    یف
    0.51
    لیکن
    0.50
     نکال
    0.50
    اهای
    0.49
    ㇁
    0.47
     یقینی
    0.47
    ൂട്ട
    0.46
     ईंधन
    0.45
    POSITIVE LOGITS
    z
    0.49
    f
    0.44
    t
    0.44
    jen
    0.43
     Darkness
    0.41
     mores
    0.40
    venes
    0.39
    :
    0.39
    orse
    0.38
    ch
    0.38
    Activations Density 0.000%

    No Known Activations