© 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. 118208
    Prev
    Next
    INDEX
    Explanations

    Q:

    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
    Tun
    -0.80
     PROBLEMS
    -0.77
    urada
    -0.76
     Tattoo
    -0.76
    वं
    -0.75
    část
    -0.75
    lemish
    -0.75
     lokale
    -0.73
    arnia
    -0.73
    onego
    -0.73
    POSITIVE LOGITS
     eventually
    0.79
     witnessed
    0.75
     básicos
    0.74
    namiento
    0.71
     estaba
    0.70
    搪
    0.70
    APPLAUSE
    0.70
     kecelakaan
    0.70
    =[[
    0.70
     playtime
    0.70
    Activations Density 0.022%

    No Known Activations