© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 105736
    Prev
    Next
    INDEX
    Explanations

    SATA, SCSI, IDE drives

    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
     But
    -1.69
     is
    -1.57
    ’,
    -1.48
     of
    -1.46
    。】
    -1.43
     would
    -1.41
    のではないでしょうか
    -1.38
     And
    -1.34
     When
    -1.31
     l
    -1.29
    POSITIVE LOGITS
    řízen
    1.45
     SATA
    1.41
     PERFECT
    1.38
    ęcz
    1.33
    ühr
    1.31
    閹
    1.29
    หรือ
    1.28
    こいつ
    1.27
     tartalmaz
    1.27
    めちゃくちゃ
    1.27
    Activations Density 0.016%

    No Known Activations