© 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. 76173
    Prev
    Next
    INDEX
    Explanations

    agreements, advice, or data

    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
    ,
    0.52
     petrochemical
    0.46
     HUM
    0.43
     held
    0.43
     the
    0.42
     ingenu
    0.42
     inch
    0.41
    oro
    0.41
    ’
    0.41
     aqueles
    0.41
    POSITIVE LOGITS
     کورٹ
    0.48
    蓊
    0.47
    断面
    0.46
    zął
    0.46
     парамет
    0.46
    志森
    0.46
     ලි
    0.45
    墓志
    0.45
    ቬ
    0.45
    寐
    0.45
    Activations Density 0.003%

    No Known Activations