© 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. 111471
    Prev
    Next
    INDEX
    Explanations

    celebrity names and associated words

    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
    🛇
    -2.48
    炻
    -2.39
    畱
    -2.28
    已经
    -2.28
    n
    -2.23
    其妙
    -2.23
    ஂ
    -2.20
    閙
    -2.20
     Atención
    -2.19
    蕖
    -2.17
    POSITIVE LOGITS
    鉭
    2.06
     einige
    2.02
    普通人
    1.98
     blatantly
    1.97
     tackling
    1.94
    邂
    1.91
     muncul
    1.91
    風の
    1.89
     戦
    1.87
    女孩子
    1.84
    Activations Density 0.002%

    No Known Activations