© 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. 104241
    Prev
    Next
    INDEX
    Explanations

    160

    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
    I
    -2.31
    龶
    -2.16
    ”;
    -2.13
    ]
    -2.13
    A
    -2.11
    鲼
    -2.08
    歺
    -1.93
    
    -1.92
     薬局
    -1.90
    ”:
    -1.87
    POSITIVE LOGITS
    ть
    2.27
    ࿙
    2.20
    itiert
    2.20
     Для
    2.05
    괭
    1.95
    ፳
    1.94
     盖
    1.89
    mathrm
    1.89
    等的
    1.86
    ación
    1.84
    Activations Density 0.012%

    No Known Activations