© 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. 130456
    Prev
    Next
    INDEX
    Explanations

    createElement, structure, Element

    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
     gleicher
    -1.60
    荩
    -1.58
    },
    -1.56
     शुर
    -1.56
     acquire
    -1.55
    O
    -1.52
     Главная
    -1.52
    更多的
    -1.51
    也都
    -1.49
     morgon
    -1.46
    POSITIVE LOGITS
     that
    1.70
     incrí
    1.53
     him
    1.52
     something
    1.52
     nggak
    1.46
     gak
    1.45
     this
    1.45
     namely
    1.36
    ти
    1.35
     pensent
    1.34
    Activations Density 0.000%

    No Known Activations