© 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. 75379
    Prev
    Next
    INDEX
    Explanations

    previous roles or events

    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
    en
    -1.90
    篳
    -1.82
    ⤻
    -1.77
     bahay
    -1.74
     naviguant
    -1.72
     különböz
    -1.71
    Ꮂ
    -1.71
    edad
    -1.71
     generando
    -1.70
    ↵↵
    -1.66
    POSITIVE LOGITS
     is
    2.20
    摃
    2.03
    Prior
    2.02
    Previously
    1.98
    潆
    1.97
    ⚋
    1.96
     fået
    1.93
    Most
    1.92
    Using
    1.88
     seperti
    1.87
    Activations Density 0.011%

    No Known Activations