© 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-16K
    7. 2596
    Prev
    Next
    INDEX
    Explanations

    take advantage

    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_16k_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
    ଞ
    1.92
    lith
    1.88
    গ্রহায়ণ
    1.87
    pump
    1.86
    ことがあります
    1.81
    िरा
    1.81
     Pudding
    1.81
     કંઈ
    1.79
    dil
    1.78
    ખી
    1.78
    POSITIVE LOGITS
    ัจ
    1.75
    [*]
    1.68
    ],
    1.61
    
    1.61
     place
    1.58
    티브
    1.54
     racine
    1.52
    [/
    1.50
    
    1.49
     advantage
    1.48
    Activations Density 0.556%

    No Known Activations