© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 86365
    Prev
    Next
    INDEX
    Explanations

    proxy usage and reflection

    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
    ↵↵
    -2.02
    柃
    -1.52
    　「
    -1.41
     verra
    -1.41
     RSITY
    -1.41
     autorité
    -1.40
    ↵
    -1.40
    πος
    -1.39
    нию
    -1.38
    ਿਆ
    -1.37
    POSITIVE LOGITS
     Якщо
    1.59
     Ersten
    1.51
    ۱۵
    1.41
     selben
    1.39
    ]
    1.38
    ۱۴
    1.38
     legions
    1.38
     vollen
    1.37
     uitgevoerd
    1.37
     meager
    1.36
    Activations Density 0.013%

    No Known Activations