© 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. 60627
    Prev
    Next
    INDEX
    Explanations

    happy to help

    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
    selbe
    -1.05
     století
    -0.98
     vendido
    -0.93
     keuntungan
    -0.93
     alot
    -0.91
     agentes
    -0.90
    FundMe
    -0.90
     detenidos
    -0.88
     coronel
    -0.87
    痨
    -0.87
    POSITIVE LOGITS
     to
    1.93
    happy
    1.64
    Happy
    1.45
     happy
    1.33
     Happy
    1.26
    About
    1.11
     campers
    1.10
     camper
    1.09
    Any
    1.03
    when
    1.00
    Activations Density 0.007%

    No Known Activations