© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 84408
    Prev
    Next
    INDEX
    Explanations

    kinds of offerings

    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
    Same
    -1.72
    к
    -1.70
     {
    
    -1.68
    鉏
    -1.63
    Different
    -1.56
    </i>
    -1.52
    Если
    -1.50
    鱚
    -1.49
    /**
    
    -1.48
    Есть
    -1.48
    POSITIVE LOGITS
     of
    2.66
    ↵↵
    1.88
    䊐
    1.84
     aching
    1.76
     类型
    1.73
     brazen
    1.70
     including
    1.66
     概要
    1.65
     noting
    1.61
     would
    1.59
    Activations Density 0.023%

    No Known Activations