© 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. 103852
    Prev
    Next
    INDEX
    Explanations

    much more + adjective

    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
    硨
    -2.94
     pérd
    -2.86
     帅气
    -2.48
    翆
    -2.34
    耵
    -2.34
    ⒝
    -2.27
    饃
    -2.25
    檮
    -2.25
    岨
    -2.25
    쨩
    -2.22
    POSITIVE LOGITS
     e
    2.08
     
    2.06
     /
    2.03
     of
    1.97
     #
    1.91
     .
    1.90
    AutoresizingMask
    1.82
     There
    1.80
    <em>
    1.80
     Not
    1.80
    Activations Density 0.010%

    No Known Activations