© 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. 104762
    Prev
    Next
    INDEX
    Explanations

    asterisk, Asteraceae, asteroids

    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
    
    -2.94
    夲
    -2.67
    ꦢ
    -2.66
    塒
    -2.64
    ⎚
    -2.58
    龘
    -2.56
    ꯲
    -2.55
     夜景
    -2.55
    饜
    -2.52
    澌
    -2.45
    POSITIVE LOGITS
            
    3.52
    :
    3.27
    </strong>
    3.17
    </h3>
    3.13
    觏
    2.97
    ]
    2.86
    .
    2.73
    -
    2.50
    !
    2.44
     Then
    2.41
    Activations Density 0.003%

    No Known Activations