© 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. 22-GEMMASCOPE-RES-131K
    7. 68452
    Prev
    Next
    INDEX
    Explanations

    win-win, win over, win all

    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_22/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
     \
    -2.70
     }
    -2.64
    ↑↑↑</
    -2.38
    閙
    -2.27
    }
    -2.25
    ]
    -2.25
     additionally
    -2.13
     proactively
    -2.08
    ”
    -2.08
     continually
    -2.06
    POSITIVE LOGITS
    狲
    2.72
     comrade
    2.47
    
    2.45
    蘩
    2.39
     کنه
    2.34
     pentru
    2.33
     angen
    2.30
    菸
    2.28
    嘞
    2.28
    咘
    2.25
    Activations Density 0.033%

    No Known Activations