© 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. 40-GEMMASCOPE-2-RES-262K
    7. 165
    Prev
    Next
    INDEX
    Explanations

    kitchen and amenities

    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_40_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
     overexpression
    0.44
     discredited
    0.44
     metastatic
    0.40
     metastable
    0.40
     metastasis
    0.40
     rebellious
    0.39
     resection
    0.39
    顎
    0.38
     defiance
    0.38
     algorit
    0.38
    POSITIVE LOGITS
     kitchenette
    1.14
     kitchen
    1.06
     amenities
    1.00
    Kitchen
    0.95
     Kitchen
    0.95
     Amenities
    0.94
     kitchens
    0.93
    廚
    0.93
    kitchen
    0.92
     cookware
    0.92
    Activations Density 0.009%

    No Known Activations