© 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. 104145
    Prev
    Next
    INDEX
    Explanations

    people and strategy

    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
    ers
    -1.68
    3
    -1.49
     extensive
    -1.48
     little
    -1.45
     use
    -1.42
     schermo
    -1.41
     large
    -1.39
    ↵↵
    -1.38
    ing
    -1.35
     Using
    -1.34
    POSITIVE LOGITS
     tramontina
    1.63
     brilla
    1.55
     ส์
    1.52
     ܙ
    1.48
     psychi
    1.48
     tremend
    1.47
     notori
    1.45
     perg
    1.45
     enig
    1.44
     нашел
    1.44
    Activations Density 0.019%

    No Known Activations