© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-65K
    7. 302
    Prev
    Next
    INDEX
    Explanations

    print function call

    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
    DVR
    0.99
     deftly
    0.97
    /',
    0.97
    を中心
    0.90
    -,
    0.89
    chts
    0.88
    }^{*}$
    0.88
    ẫu
    0.87
     kalangan
    0.87
    regulars
    0.86
    POSITIVE LOGITS
     знаком
    0.99
     об
    0.95
     "*************
    0.94
     evaluation
    0.94
     Evaluation
    0.93
     Evaluate
    0.92
     Json
    0.91
     اعلان
    0.90
     evaluate
    0.89
     пусто
    0.88
    Activations Density 0.013%

    No Known Activations