© 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. 235344
    Prev
    Next
    INDEX
    Explanations

    financial terms and structures

    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
     सर्व
    0.46
     ‪
    0.44
    സ
    0.43
     ISBN
    0.41
    ة
    0.41
    itih
    0.41
     Beck
    0.39
     رمی
    0.39
    话说
    0.39
     Sist
    0.38
    POSITIVE LOGITS
    TreeNode
    0.49
    ફેદ
    0.48
     соотно
    0.48
    ৪২
    0.47
    GROUP
    0.47
    REP
    0.47
     allora
    0.46
    PickerController
    0.46
    Threshold
    0.46
    ၷ
    0.45
    Activations Density 0.000%

    No Known Activations