© 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. 90639
    Prev
    Next
    INDEX
    Explanations

    code and structure elements

    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
     abusos
    -0.91
    CONCLUSIONS
    -0.88
     regardless
    -0.86
    หน่อย
    -0.86
    جت
    -0.85
    umblr
    -0.84
    addWidget
    -0.83
     slå
    -0.82
    Resin
    -0.77
    ⚠️
    -0.77
    POSITIVE LOGITS
     pivotal
    1.09
     li
    0.93
     ausgezeichnet
    0.93
    	
    0.89
     ситуацию
    0.87
    problema
    0.86
    li
    0.85
    ud
    0.83
    chable
    0.81
     parfaite
    0.81
    Activations Density 0.001%

    No Known Activations