© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 21325
    Prev
    Next
    INDEX
    Explanations

    air conditioning and cooling

    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_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    vertexBuffer
    0.43
     sausages
    0.41
     phospholipids
    0.41
     phospho
    0.41
    ὼ
    0.40
    ゴム
    0.39
     volunteering
    0.39
     phosphorus
    0.38
     spider
    0.38
    𒁉
    0.37
    POSITIVE LOGITS
    空调
    1.73
     HVAC
    1.66
    エアコン
    1.43
     cooling
    1.24
    HV
    1.22
     конди
    1.21
     refrigeration
    1.19
     Cooling
    1.14
    cooling
    1.12
     Heating
    1.10
    Activations Density 0.005%

    No Known Activations