© 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. 34-GEMMASCOPE-RES-131K
    7. 84757
    Prev
    Next
    INDEX
    Explanations

    code limitations

    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_34/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
    Compressed
    -0.77
     Animated
    -0.75
    磕
    -0.75
    ❃
    -0.75
    monton
    -0.75
    IMM
    -0.74
     lørdag
    -0.71
     Perr
    -0.71
     Mult
    -0.71
     prominent
    -0.71
    POSITIVE LOGITS
                                
    0.92
    0.87
                                   
    0.86
                                  
    0.85
    0.84
                                 
    0.82
    𝒊
    0.80
     nunmehr
    0.79
    agers
    0.77
     ограничения
    0.77
    Activations Density 0.026%

    No Known Activations