© 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. 34-GEMMASCOPE-RES-131K
    4. 81588
    Prev
    Next
    INDEX
    Explanations

    javacomputer programming

    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_34/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
     feminist
    -0.80
    Története
    -0.79
    无法
    -0.75
     agrup
    -0.74
     henkilö
    -0.72
    ólogo
    -0.71
    ストン
    -0.71
    酚
    -0.70
     сай
    -0.70
     suffice
    -0.70
    POSITIVE LOGITS
    xtext
    0.91
     грам
    0.90
    ANTLR
    0.89
    antlr
    0.88
    ccess
    0.85
     ürünleri
    0.81
     Sce
    0.80
     quatrième
    0.79
    jface
    0.79
    esso
    0.79
    Activations Density 0.002%

    No Known Activations