© 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. 71423
    Prev
    Next
    INDEX
    Explanations

    numbers and half

    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
     theoretically
    -2.16
    </b>
    -2.08
    塤
    -1.95
    replyreport
    -1.87
     fundamentally
    -1.85
     routinely
    -1.84
     logically
    -1.84
    when
    -1.81
    ஂ
    -1.81
     conceptually
    -1.78
    POSITIVE LOGITS
     of
    3.09
    圌
    2.17
    
    1.93
    ícias
    1.88
     brune
    1.88
    ꔹ
    1.85
    鹇
    1.85
     uncanny
    1.84
     welchem
    1.83
    嫪
    1.83
    Activations Density 0.004%

    No Known Activations