© 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. 10-GEMMASCOPE-RES-131K
    7. 111105
    Prev
    Next
    INDEX
    Explanations

    start of sentence/list item

    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_10/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
    -
    -1.82
     those
    -1.69
    :
    -1.67
    ,
    -1.54
     any
    -1.48
     S
    -1.42
     then
    -1.35
     on
    -1.34
     additional
    -1.34
     (
    -1.32
    POSITIVE LOGITS
     like
    1.55
    ']))
    1.55
     ettei
    1.44
    <!--
    1.42
    micamente
    1.42
    ()).
    1.41
     JOSE
    1.39
     ecran
    1.36
    eció
    1.35
    像
    1.33
    Activations Density 0.132%

    No Known Activations