© 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. 2361
    Prev
    Next
    INDEX
    Explanations

    on [topic]

    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
    ೆ
    2.17
    ações
    2.15
    ी
    2.13
    ा
    2.12
    at
    2.09
    ofthe
    1.88
    us
    1.86
    ો
    1.83
    ம்பிய
    1.83
    े
    1.81
    POSITIVE LOGITS
    t
    2.01
     publi
    1.93
     replete
    1.90
    мата
    1.86
     culminating
    1.85
     soiled
    1.85
    
    1.79
     refuge
    1.78
     marm
    1.75
     memperbaiki
    1.71
    Activations Density 0.196%

    No Known Activations