© 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-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 2405
    Prev
    Next
    INDEX
    Explanations

    because i

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ی
    4.12
    י
    3.76
    ি
    3.62
    이
    3.41
    𝘁
    3.29
    িং
    3.23
    ه
    3.18
    ு
    3.14
    न्स
    3.02
    ៉
    2.87
    POSITIVE LOGITS
    ї
    2.96
    ように
    2.95
    al
    2.94
    ित
    2.72
    et
    2.67
    م
    2.67
    
    2.64
    ال
    2.53
    에
    2.44
    ಿಕ
    2.43
    Activations Density 0.177%

    No Known Activations