© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 74283
    Prev
    Next
    INDEX
    Explanations

    ACE inhibitor, server, parser, International

    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
    癭
    -2.61
    鹟
    -2.55
    說
    -2.47
    悧
    -2.41
    翾
    -2.39
     Monfieur
    -2.27
    ে
    -2.27
    饜
    -2.25
     frantically
    -2.23
    簓
    -2.23
    POSITIVE LOGITS
    ↵
    3.53
    ,
    3.19
    vantaged
    2.83
    $
    2.72
    </h4>
    2.55
     "
    2.55
    a
    2.44
    </em>
    2.38
    1
    2.27
     .
    2.16
    Activations Density 0.019%

    No Known Activations