© 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. 47671
    Prev
    Next
    INDEX
    Explanations

    a/an followed by adjective or noun

    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
     exclusivamente
    -1.59
     musíte
    -1.59
     مفص
    -1.42
     cœurs
    -1.41
     vijf
    -1.41
    齜
    -1.40
     éléments
    -1.40
     its
    -1.38
    ですし
    -1.33
    espero
    -1.32
    POSITIVE LOGITS
     \
    1.33
     a
    1.30
     However
    1.30
     Erkrankung
    1.20
     may
    1.20
    </h2>
    1.18
     nhưng
    1.16
     >
    1.16
    也有
    1.15
    iburg
    1.15
    Activations Density 0.070%

    No Known Activations