© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 10628
    Prev
    Next
    INDEX
    Explanations

    org/

    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_7_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
    ിക
    3.01
    eteor
    2.82
    ្នាំ
    2.74
    
    2.67
    պ
    2.61
    কার
    2.61
    洴
    2.57
    
    2.57
    ্যালেঞ্জ
    2.56
    ことは
    2.56
    POSITIVE LOGITS
    স্তাফিজ
    2.60
    یشہ
    2.56
     hitam
    2.55
    ="#!"
    2.39
    e
    2.39
    ة
    2.32
    rate
    2.29
    ́ch
    2.25
    ein
    2.24
    rieden
    2.17
    Activations Density 0.005%

    No Known Activations