© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 128646
    Prev
    Next
    INDEX
    Explanations

    ex or Ex followed by punctuation

    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
        
    -2.98
    V
    -2.75
          
    -2.72
    J
    -2.72
    }$
    -2.61
                        
    -2.52
             
    -2.50
    </th>
    -2.44
                
    -2.41
    e
    -2.31
    POSITIVE LOGITS
    ୈ
    3.23
    TryDecode
    2.58
    鬭
    2.50
    Ꮵ
    2.48
    ilustrasi
    2.47
    鶲
    2.45
    ﮑ
    2.41
    ⃙
    2.39
    ándor
    2.28
    ؽ
    2.27
    Activations Density 0.035%

    No Known Activations