© 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. 13736
    Prev
    Next
    INDEX
    Explanations

    compound terms or technical phrases

    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
    eira
    -1.38
     alebo
    -1.32
    iant
    -1.31
     игрушки
    -1.27
    ᶻ
    -1.26
    "،
    -1.24
     mantend
    -1.23
    anato
    -1.23
    ACJA
    -1.22
    istungen
    -1.21
    POSITIVE LOGITS
     inoxid
    1.41
     this
    1.27
     while
    1.25
     second
    1.25
     waistcoat
    1.11
     recently
    1.10
    end
    1.09
     new
    1.09
    ont
    1.09
    ib
    1.07
    Activations Density 0.998%

    No Known Activations