© 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. 221438
    Prev
    Next
    INDEX
    Explanations

    closing punctuation

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

    types of copy

    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
     জাতিকে
    0.46
    TextViewStyle
    0.42
    عا
    0.41
    LinkLabel
    0.40
    猝
    0.40
    itetty
    0.40
    DataGridView
    0.40
    聩
    0.39
    odep
    0.39
    േറ്റ
    0.39
    POSITIVE LOGITS
    ची
    0.52
    FRE
    0.46
     :).
    0.45
     '{
    0.45
     LUCKY
    0.45
    GAG
    0.44
     hår
    0.44
    भाग्य
    0.43
     tais
    0.43
     fare
    0.42
    Activations Density 0.000%

    No Known Activations