© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 103268
    Prev
    Next
    INDEX
    Explanations

    dimensions and ratings

    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
    őben
    -1.84
     would
    -1.55
     it
    -1.51
     sufficiente
    -1.49
     know
    -1.49
     ήταν
    -1.46
     when
    -1.45
    🈹
    -1.44
     holdt
    -1.43
     during
    -1.38
    POSITIVE LOGITS
    ↵↵
    1.36
     مدى
    1.36
     apesar
    1.28
     handels
    1.28
     nimmer
    1.27
     &&
    1.26
     we
    1.23
     должны
    1.20
     spiegel
    1.20
    uri
    1.19
    Activations Density 0.115%

    No Known Activations