© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 66654
    Prev
    Next
    INDEX
    Explanations

    cocoa and Cocoa framework

    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
    ”
    -3.23
    “
    -2.81
    ll
    -2.80
    ers
    -2.72
                    
    -2.72
          
    -2.52
    真的很
    -2.47
     sua
    -2.38
    The
    -2.36
              
    -2.33
    POSITIVE LOGITS
    ’，
    2.94
     ]}
    2.41
    🤚
    2.34
    🤟
    2.33
    ࠬ
    2.25
     ])
    2.19
    ⑉
    2.19
    )」
    2.17
     niego
    2.17
    身后的
    2.16
    Activations Density 0.003%

    No Known Activations