© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 94287
    Prev
    Next
    INDEX
    Explanations

    dryness

    np_acts-logits-general · gemini-2.5-flash-lite

    dry season or heat

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     gable
    0.52
     postcard
    0.50
     headband
    0.46
     hourly
    0.45
    箔
    0.45
     levy
    0.45
     takePhotoButton
    0.45
     chirurg
    0.44
     župan
    0.43
     buget
    0.43
    POSITIVE LOGITS
    dry
    1.44
    Dry
    1.41
     dry
    1.38
     Dry
    1.38
     خشک
    1.21
     DRY
    1.19
     dryness
    1.18
     khô
    1.09
    干
    1.06
     drier
    1.03
    Activations Density 0.064%

    No Known Activations