© 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. 102798
    Prev
    Next
    INDEX
    Explanations

    Application class methods

    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
     glancing
    -0.87
    tengo
    -0.87
    avimas
    -0.86
    Ȑ
    -0.84
    <-
    -0.83
    сна
    -0.81
    积累
    -0.81
    šet
    -0.80
     forwarding
    -0.80
     remplacement
    -0.79
    POSITIVE LOGITS
    起身
    0.93
    jwa
    0.81
     roughly
    0.78
     歯
    0.78
    越是
    0.77
    手掌
    0.77
     surrounded
    0.76
     granny
    0.75
     prolly
    0.73
     verwacht
    0.73
    Activations Density 0.053%

    No Known Activations