© 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. 249699
    Prev
    Next
    INDEX
    Explanations

    common phrases and entities

    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
     வாகன
    0.55
     germ
    0.48
    тинен
    0.47
    ął
    0.47
    Ꮨ
    0.46
    Dieter
    0.46
    ≣
    0.46
     saisons
    0.45
    είται
    0.45
     lieux
    0.44
    POSITIVE LOGITS
    k
    0.52
     वार्
    0.51
     Wochschr
    0.51
     Reforms
    0.48
     OI
    0.47
     व्याज
    0.45
     henüz
    0.45
    may
    0.44
    ভা
    0.44
    ism
    0.44
    Activations Density 0.000%

    No Known Activations