© 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. 130716
    Prev
    Next
    INDEX
    Explanations

    numbers starting with 6

    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
    т
    -2.47
    聍
    -2.33
    
    -2.23
     sviluppo
    -2.17
    鈊
    -2.16
     is
    -2.11
     archivio
    -2.11
    úcia
    -2.06
     algunos
    -2.05
     says
    -2.02
    POSITIVE LOGITS
     
    2.91
    ’
    2.77
    }
    2.73
    </i>
    2.27
     Also
    2.22
    ’’
    2.08
    2.05
    te
    2.02
     we
    1.98
    O
    1.95
    Activations Density 0.014%

    No Known Activations