© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 9504
    Prev
    Next
    INDEX
    Explanations

    constants and continuations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_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
    >>>
    0.59
     Gat
    0.57
     หลาย
    0.56
     केंद्र
    0.55
     Gore
    0.55
    >>;
    0.55
     Fell
    0.54
     Bollywood
    0.54
     shilling
    0.54
     Buchanan
    0.53
    POSITIVE LOGITS
    úsica
    0.61
    躁
    0.59
    ल्दी
    0.58
     acciones
    0.55
     facilidad
    0.55
     ejec
    0.54
     always
    0.53
     siempre
    0.53
    encan
    0.53
     NgModule
    0.52
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.