© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 111206
    Prev
    Next
    INDEX
    Explanations

    qualifying for tournaments

    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
     newfound
    -2.11
     newly
    -1.82
     становится
    -1.70
     may
    -1.68
     burgeoning
    -1.67
    H
    -1.66
     will
    -1.66
    </h3>
    -1.61
    is
    -1.59
    va
    -1.58
    POSITIVE LOGITS
     uniquement
    1.73
     qualifier
    1.69
     autres
    1.67
    つる
    1.66
    甞
    1.66
     recettes
    1.65
    毎回
    1.63
    鼉
    1.62
    𐐀
    1.59
     raison
    1.59
    Activations Density 0.017%

    No Known Activations