© 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. 3767
    Prev
    Next
    INDEX
    Explanations

    theatrical productions and performances

    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
    \
    -1.52
     you
    -1.48
    _{
    -1.46
    </tr>
    -1.46
    $.
    -1.40
     /
    -1.32
     should
    -1.29
     since
    -1.27
     there
    -1.27
     correspondiente
    -1.27
    POSITIVE LOGITS
     phare
    1.56
     confirme
    1.52
     apparence
    1.51
     habile
    1.51
     rapor
    1.51
     idee
    1.47
     liquide
    1.46
     manifeste
    1.45
     aboli
    1.43
     estime
    1.42
    Activations Density 0.034%

    No Known Activations