© 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. 112704
    Prev
    Next
    INDEX
    Explanations

    rivers and river valleys

    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
    </strong>
    -3.09
    .";
    -1.98
    谞
    -1.78
    猀
    -1.68
     駅前
    -1.68
    ほとん
    -1.66
    比较好
    -1.66
    灕
    -1.66
    
    -1.63
    ۲
    -1.62
    POSITIVE LOGITS
    </h5>
    1.94
    </td>
    1.91
     You
    1.67
     If
    1.57
     But
    1.52
     вещь
    1.47
     &
    1.45
     文
    1.45
     reduce
    1.44
    "
    1.44
    Activations Density 0.021%

    No Known Activations