© 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. 10096
    Prev
    Next
    INDEX
    Explanations

    informed decisions and consent

    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
    阏
    -1.78
    Ꮠ
    -1.75
    哙
    -1.75
    蟊
    -1.75
    𓁹
    -1.74
    bemos
    -1.61
     réaliser
    -1.61
    쳇
    -1.57
     reinigen
    -1.57
    íble
    -1.54
    POSITIVE LOGITS
    *
    1.82
    .
    1.69
    Each
    1.65
    These
    1.48
     approach
    1.44
     educated
    1.41
     expectations
    1.38
    Both
    1.34
     carefully
    1.33
    Every
    1.29
    Activations Density 0.014%

    No Known Activations