© 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. 34-GEMMASCOPE-RES-131K
    7. 33539
    Prev
    Next
    INDEX
    Explanations

    DOCTYPE PUBLIC declarations

    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
     toppers
    -0.73
    background
    -0.71
    toprule
    -0.68
     проми
    -0.68
     نشده
    -0.67
     inconsist
    -0.66
    agir
    -0.66
     METH
    -0.66
    maro
    -0.66
    nup
    -0.65
    POSITIVE LOGITS
    cartItem
    0.71
     Trail
    0.69
     Barton
    0.68
     trail
    0.67
     cau
    0.66
     brukar
    0.65
     encar
    0.65
     agents
    0.64
     géographie
    0.64
    覺
    0.63
    Activations Density 0.083%

    No Known Activations