© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-16K
    7. 7805
    Prev
    Next
    INDEX
    Explanations

    fun activities, facts, or events

    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_40_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    Reflection
    0.42
    为何
    0.41
    สบาย
    0.40
    Evaluation
    0.40
    ऑस्ट्रेलिया
    0.39
    Tet
    0.39
     खूबसूरती
    0.39
     价
    0.39
     চাহিল
    0.39
     Règlement
    0.39
    POSITIVE LOGITS
     fun
    0.82
     Fun
    0.75
    fun
    0.71
     FUN
    0.70
     funnel
    0.65
    niest
    0.61
    Fun
    0.61
    icular
    0.59
     diversión
    0.59
    FUN
    0.58
    Activations Density 0.055%

    No Known Activations