© 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. 48045
    Prev
    Next
    INDEX
    Explanations

    all are

    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
     is
    -1.58
    setBold
    -1.52
    兩
    -1.45
     willpower
    -1.41
    ativement
    -1.40
    minton
    -1.37
    蔼
    -1.36
    moreland
    -1.34
    these
    -1.32
    żdż
    -1.32
    POSITIVE LOGITS
     فقط
    1.63
    简单的
    1.58
    tería
    1.53
    大多
    1.53
     сказал
    1.52
    grafico
    1.48
    şek
    1.47
    
    1.46
     VERY
    1.45
     الذين
    1.40
    Activations Density 0.017%

    No Known Activations