© 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. 15166
    Prev
    Next
    INDEX
    Explanations

    оказалось, quedar, okazawa, ocassionally

    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
    꽤
    -2.33
     to
    -2.25
     科
    -2.03
    تها
    -2.02
     探
    -2.00
    艫
    -1.95
    梘
    -1.94
    C
    -1.92
    姈
    -1.91
    lynol
    -1.90
    POSITIVE LOGITS
    ’
    3.73
    </em>
    2.27
    ет
    2.25
     
    2.19
    鍇
    2.14
    </strong>
    2.08
     ancianos
    2.05
     was
    2.03
    2.02
    </h4>
    1.94
    Activations Density 0.001%

    No Known Activations