© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 14694
    Prev
    Next
    INDEX
    Explanations

    recent history currently known

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     myös
    -0.89
     these
    -0.86
     daarom
    -0.85
    ὸς
    -0.85
     aufgrund
    -0.82
     ursprünglichen
    -0.79
     purported
    -0.79
    Личная
    -0.79
    ouin
    -0.78
     vielleicht
    -0.78
    POSITIVE LOGITS
     извест
    1.30
     recent
    1.21
     known
    1.18
     current
    1.14
     recently
    1.11
     znám
    1.11
     معروف
    1.10
    Recently
    1.07
     populer
    1.07
     currently
    1.05
    Activations Density 0.061%

    No Known Activations