© 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
    5. 53-GEMMASCOPE-2-RES-65K
    7. 8405
    Prev
    Next
    INDEX
    Explanations

    what is required

    np_acts-logits-general · gemini-2.5-flash-lite

    what is required

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ആഘോഷ
    0.38
    用来
    0.38
    enak
    0.36
    aksanakan
    0.34
     سيدنا
    0.34
     मानो
    0.34
     दिलचस्पी
    0.34
    针
    0.34
     ṣe
    0.33
    లుగా
    0.33
    POSITIVE LOGITS
     require
    4.34
     requires
    4.25
    require
    4.06
     requiring
    4.06
    requires
    3.95
     Require
    3.95
     Requires
    3.86
     requiere
    3.73
    Requires
    3.70
    Require
    3.64
    Activations Density 0.413%

    No Known Activations