© 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. 12022
    Prev
    Next
    INDEX
    Explanations

    details of something

    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
     acoged
    -1.10
    ategories
    -1.09
    什么呢
    -1.07
     iconos
    -0.96
     принял
    -0.96
     trampa
    -0.94
    dengan
    -0.93
    ❮
    -0.93
    servicios
    -0.93
    sü
    -0.93
    POSITIVE LOGITS
     of
    3.70
     about
    2.11
     regarding
    1.50
     kuhusu
    1.43
     siitä
    1.33
     details
    1.29
     thereof
    1.24
     such
    1.19
     concerning
    1.17
    of
    1.15
    Activations Density 0.032%

    No Known Activations