© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 7148
    Prev
    Next
    INDEX
    Explanations

    cooking and ingredients

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_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
     정책
    0.75
     финансо
    0.73
     कानून
    0.73
     জনগণের
    0.71
     kriminal
    0.71
     öffentlich
    0.68
    정책
    0.66
    괵
    0.65
     паліты
    0.64
     हितों
    0.64
    POSITIVE LOGITS
     cottura
    1.04
     flour
    1.02
     cuisson
    1.00
     cooking
    0.99
     buttermilk
    0.97
     ingredientes
    0.96
     recipes
    0.93
     ingredients
    0.91
     harina
    0.91
     butter
    0.90
    Activations Density 0.378%

    No Known Activations