© 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. 1597
    Prev
    Next
    INDEX
    Explanations

    what the future holds

    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
     levier
    -1.63
    選べる
    -1.63
     grootste
    -1.54
     réservoir
    -1.54
    łóż
    -1.53
     laatste
    -1.52
    cisive
    -1.52
    yyv
    -1.52
     allerede
    -1.50
    鉏
    -1.49
    POSITIVE LOGITS
    j
    1.91
    f
    1.78
    (
    1.66
    {
    1.61
    L
    1.55
    in
    1.53
    x
    1.51
     in
    1.50
    You
    1.45
    ’
    1.45
    Activations Density 0.016%

    No Known Activations