© 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. 16-GEMMASCOPE-2-RES-262K
    7. 6490
    Prev
    Next
    INDEX
    Explanations

    people and their characteristics

    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_16_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
    ك
    0.86
    as
    0.68
    os
    0.59
    ح
    0.57
    كيف
    0.57
    يا
    0.53
     be
    0.52
    خ
    0.51
    ler
    0.50
    to
    0.50
    POSITIVE LOGITS
    ни
    0.49
    ,
    0.49
    ’)
    0.47
     who
    0.45
    ’
    0.44
    <0x80>
    0.43
     человеку
    0.40
    еха
    0.39
    ized
    0.39
    ть
    0.38
    Activations Density 0.328%

    No Known Activations