© 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. 65553
    Prev
    Next
    INDEX
    Explanations

    . #

    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
     Gallen
    -0.73
     COMO
    -0.72
     Clears
    -0.69
     prisma
    -0.66
    🍼
    -0.66
    Elizabeth
    -0.65
     REFUND
    -0.65
    Histor
    -0.65
     engag
    -0.65
    czyna
    -0.64
    POSITIVE LOGITS
    Gen
    0.76
    hyphen
    0.68
     IDE
    0.68
     Twitter
    0.66
    мей
    0.66
     repeated
    0.65
     Gen
    0.64
    陣
    0.64
    ロボ
    0.64
     TABLE
    0.64
    Activations Density 0.066%

    No Known Activations