© 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. 70551
    Prev
    Next
    INDEX
    Explanations

    also introducing additional points

    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
    ),
    -2.05
    ).
    -1.88
     двух
    -1.87
    </td>
    -1.87
    出た
    -1.81
     знаешь
    -1.81
     прошла
    -1.81
    %;
    -1.79
    %',
    -1.78
     also
    -1.77
    POSITIVE LOGITS
    所以我
    2.39
    我只
    2.19
    
    1.95
    を描く
    1.94
    wendig
    1.93
    ᷆
    1.88
     they
    1.84
    ⢫
    1.84
    鲧
    1.83
    我一直
    1.80
    Activations Density 0.007%

    No Known Activations