© 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. 39354
    Prev
    Next
    INDEX
    Explanations

    FILE and DIR types

    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
     если
    -1.69
    various
    -1.63
     sensazione
    -1.56
    нных
    -1.55
     ajouter
    -1.51
     jika
    -1.45
    different
    -1.45
    
    -1.43
     esigen
    -1.43
    ICOLON
    -1.40
    POSITIVE LOGITS
    ांकि
    1.73
    </em>
    1.54
    <bos>
    1.45
    䤀
    1.34
    </h4>
    1.28
    ابراین
    1.27
    oinette
    1.25
    FABRIC
    1.22
    жник
    1.21
     }
    1.20
    Activations Density 0.009%

    No Known Activations