© 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. 65890
    Prev
    Next
    INDEX
    Explanations

    positive attributes and options

    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
    ឬ
    -1.13
    ——–
    -1.12
     masina
    -1.06
     biografi
    -1.04
     fatale
    -1.01
     komik
    -1.01
    ៍
    -0.99
    —————
    -0.98
     moſt
    -0.98
    nologi
    -0.98
    POSITIVE LOGITS
     way
    2.27
     addition
    1.94
     start
    1.48
     starting
    1.48
     example
    1.40
     opportunity
    1.38
     ways
    1.29
     first
    1.23
     option
    1.22
     reminder
    1.21
    Activations Density 0.029%

    No Known Activations