© 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. 10-GEMMASCOPE-RES-131K
    7. 9523
    Prev
    Next
    INDEX
    Explanations

    Univ, POV, QObject, AFL, TCS prefixes

    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
     \
    -3.06
    I
    -2.81
    \
    -2.78
    *
    -2.78
    ᥀
    -2.64
    箆
    -2.39
    两年
    -2.38
     одна
    -2.34
    ]
    -2.30
    $
    -2.25
    POSITIVE LOGITS
    ים
    3.25
    s
    3.09
    蹰
    2.94
    也会
    2.78
    ی
    2.66
     ก็
    2.66
    鋱
    2.66
    siven
    2.61
    
    2.61
     cũng
    2.58
    Activations Density 0.005%

    No Known Activations