© 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. 12028
    Prev
    Next
    INDEX
    Explanations

    common phrases involving ghost

    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
    )
    -2.50
     waren
    -2.34
    -2.31
    蔸
    -2.30
    ↵↵
    -2.22
    (
    -2.19
     Nachfrage
    -2.17
     Erfüllung
    -2.13
     erforderlichen
    -2.11
     også
    -2.09
    POSITIVE LOGITS
    蜮
    3.52
    }
    2.39
    ⢊
    2.34
     大全
    2.30
    逹
    2.22
    arynx
    2.14
     これ
    2.14
     proactive
    2.14
    орк
    2.13
    >
    2.09
    Activations Density 0.003%

    No Known Activations