© 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. 1551
    Prev
    Next
    INDEX
    Explanations

    approaching completion or end

    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
     unrelenting
    -2.97
     enormous
    -2.95
     plethora
    -2.86
     undeniably
    -2.81
     dazzling
    -2.75
     noteworthy
    -2.73
     burgeoning
    -2.73
     unusually
    -2.72
     eleven
    -2.70
     sizeable
    -2.69
    POSITIVE LOGITS
     lauded
    3.16
    actéristi
    2.97
     REALLY
    2.89
     VERY
    2.84
     funcionamento
    2.77
     .......
    2.75
     strikingly
    2.70
     decidedly
    2.69
     merciless
    2.64
     escre
    2.63
    Activations Density 0.030%

    No Known Activations