© 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. 104115
    Prev
    Next
    INDEX
    Explanations

    bowl, North, West, fair

    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
     monstru
    -1.40
    法规
    -1.37
    美味しかったです
    -1.31
    蕯
    -1.28
    {
    -1.27
    说过
    -1.26
    美味しいです
    -1.25
    有哪些
    -1.24
    をしています
    -1.24
     divino
    -1.23
    POSITIVE LOGITS
     '
    1.73
     čia
    1.45
    RTHOOK
    1.45
    eddable
    1.41
    tometer
    1.39
    ons
    1.37
    Sciences
    1.35
    ţa
    1.34
     in
    1.34
     of
    1.33
    Activations Density 0.110%

    No Known Activations