© 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. 76176
    Prev
    Next
    INDEX
    Explanations

    health care, savings tax, ordered online, lien reduction

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

    missing or no symptoms

    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
    Not in Any Lists

    No Comments

    Negative Logits
    おそらく
    0.53
    لک
    0.50
     えっと
    0.49
    BlockUsed
    0.48
    限
    0.48
     افز
    0.48
     เพิ่ม
    0.48
     موسم
    0.46
    лма
    0.46
     ограничењима
    0.46
    POSITIVE LOGITS
     specialists
    0.51
     plough
    0.48
    +,
    0.48
     on
    0.48
     upon
    0.48
     scholar
    0.47
    represent
    0.47
     president
    0.47
    thick
    0.46
     as
    0.46
    Activations Density 0.001%

    No Known Activations