© 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. 1669
    Prev
    Next
    INDEX
    Explanations

    industry manufacturing production engineering

    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
     aback
    3.06
    ஜ்மஹால்
    2.66
    나
    2.63
    笄
    2.61
     diffusion
    2.60
     Meski
    2.54
    िडिओ
    2.50
     pomer
    2.47
    olutely
    2.47
    ஜ்மஹ
    2.45
    POSITIVE LOGITS
    螂
    2.78
     постара
    2.78
    یل
    2.76
    
    2.69
    vous
    2.69
    カイブ
    2.61
    da
    2.59
    }=\
    2.57
    }")
    2.56
    }=
    2.55
    Activations Density 0.425%

    No Known Activations