© 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. 34-GEMMASCOPE-RES-131K
    7. 108503
    Prev
    Next
    INDEX
    Explanations

    headings and specific phrases

    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_34/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
     after
    -1.33
     before
    -1.15
     almost
    -1.12
     what
    -1.08
     although
    -1.05
     Almost
    -1.05
     What
    -1.03
     from
    -1.02
     became
    -0.97
     for
    -0.96
    POSITIVE LOGITS
    ouvrir
    1.07
     horrid
    1.04
     новую
    1.02
    particularly
    0.96
     debacle
    0.96
    including
    0.94
     .........
    0.94
    oops
    0.93
     terri
    0.93
    柔らかい
    0.93
    Activations Density 0.020%

    No Known Activations