© 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. 213421
    Prev
    Next
    INDEX
    Explanations

    illness insurance, ultimate roller

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

    linking clauses and contexts

    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
    ালন
    0.45
    ॢ
    0.43
    SplitContainer
    0.42
    彧
    0.42
     mitten
    0.41
     HUR
    0.41
     থাকলেও
    0.40
    剂量
    0.40
    Cells
    0.40
     miljø
    0.39
    POSITIVE LOGITS
    ̣t
    0.63
    gegen
    0.54
     Einf
    0.52
    Д
    0.50
    ouncing
    0.50
    Т
    0.50
    ISE
    0.50
     گوئ
    0.48
     demeure
    0.48
     angered
    0.48
    Activations Density 0.000%

    No Known Activations