© 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-65K
    7. 12047
    Prev
    Next
    INDEX
    Explanations

    similar words and comparisons

    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
     क्षेत्र
    0.41
    霸
    0.40
     अच
    0.39
    ➷
    0.38
    Пу
    0.37
    kari
    0.37
     ಜಾ
    0.37
    穸
    0.37
    𝒸
    0.37
    佹
    0.37
    POSITIVE LOGITS
     similar
    2.52
     similaire
    2.23
    similar
    2.19
    Similar
    2.14
     Similar
    2.13
     similares
    2.03
     podob
    1.98
     مشابه
    1.98
     ähn
    1.98
     similaires
    1.95
    Activations Density 0.475%

    No Known Activations