© 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. 84521
    Prev
    Next
    INDEX
    Explanations

    grades and their levels

    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
     Thirteenth
    -1.48
     eleventh
    -1.45
     Eighteenth
    -1.34
     sixteenth
    -1.28
     nineteenth
    -1.22
    瓒
    -1.21
     ninth
    -1.20
     thirteenth
    -1.20
     eighteenth
    -1.18
     Twentieth
    -1.18
    POSITIVE LOGITS
     II
    1.18
    鏗
    1.17
     III
    1.07
     One
    0.93
     kurzer
    0.92
    Shift
    0.91
    Tune
    0.90
     ۲
    0.89
     dzięki
    0.88
     ۱
    0.85
    Activations Density 0.085%

    No Known Activations