© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B
    3. 41-GEMMASCOPE-2-RES-65K
    4. 14554
    Prev
    Next
    INDEX
    Explanations

    HTML attributes

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     class
    0.79
    '/>
    0.70
    }"/>
    0.63
    </img>
    0.62
    "/>
    0.62
    class
    0.61
    readonly
    0.59
     Harvest
    0.57
    /"><
    0.57
     Yosemite
    0.57
    POSITIVE LOGITS
    className
    1.52
     className
    1.36
     htmlFor
    0.96
     onClick
    0.86
    onClick
    0.86
     variants
    0.84
    variants
    0.83
    variant
    0.82
     defaultValue
    0.80
     variant
    0.80
    Activations Density 0.000%

    No Known Activations