© 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. 1322
    Prev
    Next
    INDEX
    Explanations

    expected outcomes or improvements

    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
    ب
    2.90
    ع
    2.90
    ⎥
    2.71
     fend
    2.58
    
    2.47
    ото
    2.46
    ge
    2.45
    ny
    2.42
    ‍♀
    2.39
    ू
    2.35
    POSITIVE LOGITS
     acabou
    3.05
     llegada
    2.94
     увидеть
    2.75
     изменения
    2.73
     demise
    2.65
    ંગ
    2.63
     juegan
    2.61
     जिन
    2.59
     lancio
    2.50
     nada
    2.50
    Activations Density 0.336%

    No Known Activations