© 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. 100438
    Prev
    Next
    INDEX
    Explanations

    sentence end punctuation followed by new clause

    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
     you
    -2.53
    ૉ
    -2.25
     usando
    -2.05
    didn
    -2.05
     principalement
    -2.02
     créer
    -1.88
     soooo
    -1.86
     kinda
    -1.85
    Doesn
    -1.85
     spécialement
    -1.82
    POSITIVE LOGITS
     with
    2.03
     vehemently
    1.96
     perplexing
    1.92
    ???:
    1.91
     Putting
    1.91
     after
    1.88
     unrelenting
    1.88
     dazzling
    1.88
     as
    1.86
     Those
    1.86
    Activations Density 0.021%

    No Known Activations