© 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. 127779
    Prev
    Next
    INDEX
    Explanations

    company names and databases like AdventureWorks

    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
    珢
    -3.02
    茕
    -2.86
     ſuch
    -2.69
    section
    -2.64
    〬
    -2.58
    憮
    -2.55
    罍
    -2.53
    翆
    -2.52
    辚
    -2.52
    ization
    -2.42
    POSITIVE LOGITS
    works
    2.94
    ();
    2.88
    </h3>
    2.84
    It
    2.69
     Works
    2.67
    </em>
    2.56
    я
    2.44
     You
    2.41
    </sup>
    2.38
    .
    2.31
    Activations Density 0.012%

    No Known Activations