© 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. 112714
    Prev
    Next
    INDEX
    Explanations

    Rafael followed by surnames and tournaments

    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
    —
    -2.03
    //
    -1.98
     /
    -1.93
    "
    -1.89
    </strong>
    -1.86
    </em>
    -1.81
    </sup>
    -1.80
     These
    -1.79
     :
    -1.77
    *
    -1.74
    POSITIVE LOGITS
    ᥬ
    2.13
    鶫
    1.81
     撮っ
    1.79
    蟶
    1.74
    
    1.70
    ܔ
    1.66
     Colegio
    1.65
    ándose
    1.63
    蘩
    1.63
    Ꭳ
    1.61
    Activations Density 0.007%

    No Known Activations