© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 129094
    Prev
    Next
    INDEX
    Explanations

    retrograde, superiority, grandiose, lowland

    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
    ",
    -2.83
     This
    -2.72
     unrelenting
    -2.63
    Ꮸ
    -2.58
     HUGE
    -2.52
     resolute
    -2.50
     groundbreaking
    -2.50
     perplexing
    -2.50
     unwavering
    -2.45
    銪
    -2.44
    POSITIVE LOGITS
     continually
    3.22
     remarkably
    3.17
     vastly
    3.06
    缡
    3.00
     significantly
    3.00
     predominantly
    2.94
     strikingly
    2.89
     exceptionally
    2.86
    霂
    2.84
     largely
    2.77
    Activations Density 0.003%

    No Known Activations