© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 1219
    Prev
    Next
    INDEX
    Explanations

    foo or bar

    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
    蛱
    -1.90
     reprez
    -1.60
    ﻒ
    -1.59
    臵
    -1.48
    
    -1.48
    腚
    -1.48
    </h5>
    -1.48
     conster
    -1.46
    荭
    -1.45
    媗
    -1.45
    POSITIVE LOGITS
    </strong>
    1.91
    );
    1.73
    }$
    1.61
     $
    1.52
    ":
    1.51
    ':
    1.48
     both
    1.48
    If
    1.48
    )";
    1.48
     segala
    1.47
    Activations Density 0.025%

    No Known Activations