© 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. 87383
    Prev
    Next
    INDEX
    Explanations

    some research or activity

    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
     that
    -1.57
    espé
    -1.52
     Geschenk
    -1.52
     olvidar
    -1.46
     sufficient
    -1.42
     your
    -1.42
    ൅
    -1.40
     твое
    -1.39
     internacionales
    -1.38
     kişilik
    -1.38
    POSITIVE LOGITS
     दूसरे
    1.52
    ")
    1.48
    </em>
    1.44
     jule
    1.41
    мость
    1.37
     échelle
    1.36
     eius
    1.34
    
    1.34
     décret
    1.34
     =
    1.33
    Activations Density 0.031%

    No Known Activations