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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 6297
    Prev
    Next
    INDEX
    Explanations

    helpful AI purpose

    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
    o
    2.01
    StringSet
    1.98
    ڈن
    1.93
    靼
    1.88
    vDash
    1.86
    ρθρο
    1.82
    CallbackContext
    1.81
    vdd
    1.79
    
    1.78
    ாந்து
    1.77
    POSITIVE LOGITS
     Cheng
    2.44
     Zhong
    2.43
     Ying
    2.37
     Confucian
    2.37
    Yun
    2.36
    Wei
    2.34
     Qing
    2.34
    ],"
    2.33
     Zhao
    2.32
     yuan
    2.30
    Activations Density 0.865%

    No Known Activations