© 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. 21427
    Prev
    Next
    INDEX
    Explanations

    viewed as

    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
    鑪
    -1.72
    鐿
    -1.67
    @$
    -1.54
    ﺢ
    -1.52
    躂
    -1.51
    ꯲
    -1.47
     Anſ
    -1.45
    𓂀
    -1.45
    endfor
    -1.45
     herr
    -1.45
    POSITIVE LOGITS
     it
    2.11
    .
    1.94
    </h3>
    1.68
     --
    1.41
     has
    1.40
    By
    1.39
     stroll
    1.34
    ]
    1.32
     /
    1.30
     -
    1.30
    Activations Density 0.035%

    No Known Activations