© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 68357
    Prev
    Next
    INDEX
    Explanations

    events of

    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_10/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
     iſt
    -2.02
    臜
    -1.99
    鱨
    -1.96
    妡
    -1.91
    蟊
    -1.88
    ꯷
    -1.84
     ſch
    -1.81
    '</
    -1.81
     特写
    -1.80
     amikor
    -1.79
    POSITIVE LOGITS
    b
    2.13
     intricacies
    1.88
    f
    1.88
     diligent
    1.81
     -
    1.79
     began
    1.76
     events
    1.76
     one
    1.71
     surrounding
    1.63
     seductive
    1.60
    Activations Density 0.013%

    No Known Activations