© 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. 104671
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions, ratios, or conditions

    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
     deſt
    -2.02
     miſ
    -1.81
     moſt
    -1.77
     juſt
    -1.74
    viembre
    -1.73
     rapidement
    -1.72
    ==""){
    -1.70
     perſ
    -1.68
    спользу
    -1.66
    蟜
    -1.66
    POSITIVE LOGITS
     but
    2.42
    Those
    2.09
    .
    2.05
    Although
    1.89
    Despite
    1.82
    𓏸
    1.74
    Considering
    1.70
    During
    1.68
    もし
    1.68
    Going
    1.67
    Activations Density 0.030%

    No Known Activations