© 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. 8457
    Prev
    Next
    INDEX
    Explanations

    loving

    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
    哢
    -2.78
     بنات
    -1.95
    
    -1.91
    </strong>
    -1.91
    рення
    -1.91
    étricas
    -1.89
    ्टर
    -1.89
    嫗
    -1.88
     炒め
    -1.86
    鉿
    -1.84
    POSITIVE LOGITS
    AND
    2.22
    -
    2.17
    2
    2.17
    "
    2.14
    ↵
    2.11
     charismatic
    2.11
    AN
    2.09
    <i>
    2.06
    AR
    1.98
    <b>
    1.93
    Activations Density 0.043%

    No Known Activations