© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 10216
    Prev
    Next
    INDEX
    Explanations

    products and sourcing

    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_262k_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
    ০
    1.99
    u
    1.73
    霆
    1.66
    у
    1.62
    tle
    1.62
    alingrad
    1.61
    आज
    1.50
    પણે
    1.48
    ে
    1.48
     ontological
    1.47
    POSITIVE LOGITS
     bye
    1.60
    
    1.40
     items
    1.37
    getItemId
    1.36
    stuff
    1.36
     lecz
    1.29
     sized
    1.29
     useNewUrlParser
    1.28
    itemName
    1.27
     хар
    1.26
    Activations Density 0.123%

    No Known Activations