© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43479
    Prev
    Next
    INDEX
    Explanations

    meeting people and entities

    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
     of
    -1.93
    6
    -1.92
    4
    -1.91
    </em>
    -1.91
    as
    -1.83
    5
    -1.82
    他在
    -1.80
    もし
    -1.80
    ↵
    -1.80
    case
    -1.77
    POSITIVE LOGITS
    上学
    1.94
    躂
    1.93
     multitud
    1.86
    縂
    1.86
    ꧁
    1.85
     破解
    1.85
     escondido
    1.84
     adorno
    1.80
    內容簡介
    1.80
     traduire
    1.80
    Activations Density 0.035%

    No Known Activations