© 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. 123634
    Prev
    Next
    INDEX
    Explanations

    "partly" followed by explanation

    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
    ↵
    -2.66
     tetapi
    -2.64
     The
    -2.47
     biß
    -2.34
     weich
    -2.20
    I
    -2.20
    {
    -2.17
    чика
    -2.17
    <td>
    -2.09
    $
    -1.98
    POSITIVE LOGITS
    峮
    2.73
     insinu
    2.67
    裊
    2.58
    鉏
    2.58
    釤
    2.55
     dirait
    2.48
    櫚
    2.47
    廡
    2.45
    鹇
    2.42
    豳
    2.38
    Activations Density 0.002%

    No Known Activations