© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 118905
    Prev
    Next
    INDEX
    Explanations

    common words and 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
    ——”
    -1.64
     tages
    -1.53
     ofic
    -1.53
    !»
    -1.52
    thats
    -1.52
     wann
    -1.45
    ggere
    -1.45
     Amerika
    -1.43
     impon
    -1.43
    Detalhes
    -1.42
    POSITIVE LOGITS
     not
    2.42
     like
    1.71
     say
    1.70
     still
    1.70
     never
    1.70
     require
    1.69
     lost
    1.64
     now
    1.60
     on
    1.59
     see
    1.59
    Activations Density 0.020%

    No Known Activations