© 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. 48441
    Prev
    Next
    INDEX
    Explanations

    Chang, Fuller, fullest

    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
    龊
    -2.80
    。</
    -2.50
    蓠
    -2.44
    喜歡的
    -2.38
     információ
    -2.34
     rígido
    -2.31
     solicitó
    -2.30
    
    -2.30
    uhh
    -2.30
    があれば
    -2.30
    POSITIVE LOGITS
    ]
    3.56
    s
    3.28
    *
    2.89
    of
    2.88
     они
    2.83
     =
    2.83
    4
    2.83
    –
    2.83
            
    2.78
                             
    2.77
    Activations Density 0.007%

    No Known Activations