© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 10016
    Prev
    Next
    INDEX
    Explanations

    hassle, fuss, hectic

    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
    豨
    -2.95
     sagrado
    -2.75
     silencioso
    -2.66
    摃
    -2.66
     guerrero
    -2.66
     australiano
    -2.64
     profeta
    -2.59
     condicionado
    -2.58
     rosario
    -2.48
     atendido
    -2.48
    POSITIVE LOGITS
    or
    2.63
    ↵
    2.50
     $
    2.48
    ta
    2.48
    so
    2.47
    r
    2.41
    and
    2.34
     "
    2.33
    0
    2.28
     crap
    2.27
    Activations Density 0.003%

    No Known Activations