© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 82267
    Prev
    Next
    INDEX
    Explanations

    FROM THE DISTRICT COURT

    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
    </>
    
    -0.79
     Tiefen
    -0.79
     explí
    -0.78
    gusting
    -0.75
    
    -0.74
    ěl
    -0.70
     /\.(
    -0.70
     MutableLiveData
    -0.69
    nitz
    -0.68
    /+
    -0.68
    POSITIVE LOGITS
     Yakima
    0.87
     Wap
    0.80
    omeric
    0.76
     pleural
    0.72
     追加
    0.69
     mst
    0.69
    lleri
    0.68
     alp
    0.67
     sime
    0.67
     biopsies
    0.66
    Activations Density 0.008%

    No Known Activations