© 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. 70386
    Prev
    Next
    INDEX
    Explanations

    edge or edges

    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
    .”
    -1.77
    .
    -1.74
    ”
    -1.70
     弾
    -1.56
     a
    -1.51
    ,”
    -1.47
    IN
    -1.40
     =
    -1.38
     имел
    -1.38
    <td>
    -1.38
    POSITIVE LOGITS
    罅
    1.84
     edge
    1.81
    古老
    1.79
     этих
    1.78
     diesem
    1.72
    他在
    1.66
     入っ
    1.63
     applause
    1.57
     หร
    1.55
     orchestrated
    1.54
    Activations Density 0.027%

    No Known Activations