© 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. 34-GEMMASCOPE-RES-131K
    4. 119189
    Prev
    Next
    INDEX
    Explanations

    apache license

    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_34/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
     اپل
    -0.75
     recombination
    -0.70
     libri
    -0.70
    ordeel
    -0.68
    Annie
    -0.67
     Landry
    -0.66
    kloped
    -0.66
     appealed
    -0.66
     Relaxation
    -0.66
    쌀
    -0.66
    POSITIVE LOGITS
    nili
    0.68
    ptăm
    0.66
    tch
    0.65
    oscar
    0.63
    给予
    0.63
    __((
    0.63
    ))=\
    0.63
    MARKET
    0.63
    ILLING
    0.63
     sicher
    0.63
    Activations Density 0.077%

    No Known Activations