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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 15819
    Prev
    Next
    INDEX
    Explanations

    bedroom and bathroom counts

    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
    }$-(
    0.39
     refuted
    0.39
     adjuvant
    0.38
     प्रश्न
    0.38
     ArrayRef
    0.38
    മിഷ
    0.38
     discredited
    0.38
     preamble
    0.37
    olecules
    0.36
     :,
    0.36
    POSITIVE LOGITS
     bedrooms
    1.17
     Bedrooms
    0.99
     bathrooms
    0.91
     rooms
    0.88
     bedroom
    0.84
     Bedroom
    0.81
    bedroom
    0.79
    卧室
    0.78
    Rooms
    0.77
    bedrooms
    0.76
    Activations Density 0.015%

    No Known Activations