© 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. 130747
    Prev
    Next
    INDEX
    Explanations

    awards and achievements

    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
     nuages
    -1.16
     malheure
    -1.16
     souris
    -1.12
     arbres
    -1.12
     they
    -1.10
     levure
    -1.10
     fumée
    -1.10
     congrès
    -1.10
    zioni
    -1.09
     coussin
    -1.09
    POSITIVE LOGITS
     "
    1.60
     how
    1.55
     who
    1.54
     this
    1.30
    </i>
    1.23
     which
    1.22
     способствует
    1.21
    </h5>
    1.20
     conozco
    1.19
    -};
    1.16
    Activations Density 0.122%

    No Known Activations