© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-65K
    7. 567
    Prev
    Next
    INDEX
    Explanations

    `; set` code pattern

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_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
     proble
    0.99
     aggregating
    0.99
     attributing
    0.96
     dra
    0.96
     juxtap
    0.95
    -”
    0.93
     beset
    0.92
     aggregated
    0.91
     predominantly
    0.91
     hostile
    0.90
    POSITIVE LOGITS
     Untuk
    1.89
     Sedangkan
    1.75
     また
    1.74
    そして
    1.68
    Untuk
    1.60
     ス
    1.55
     Sementara
    1.54
     その
    1.53
    また
    1.52
     وأ
    1.51
    Activations Density 0.013%

    No Known Activations