© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 136839
    Prev
    Next
    INDEX
    Explanations

    houses, buildings, and fixtures

    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
    修理
    0.47
     যন্ত্র
    0.42
    砶
    0.42
     locksmith
    0.41
     віднов
    0.40
     восстанов
    0.40
     ذمہ
    0.40
    粓
    0.39
    Repair
    0.39
    ུང་
    0.39
    POSITIVE LOGITS
     facilities
    0.53
     luxuries
    0.50
    시설
    0.46
     oceans
    0.44
     improvements
    0.44
     enhancements
    0.44
     arteries
    0.43
     networks
    0.43
     arguments
    0.43
    এন
    0.43
    Activations Density 0.007%

    No Known Activations