© 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. 129564
    Prev
    Next
    INDEX
    Explanations

    toast and toaster

    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
    th
    -1.84
    fficking
    -1.72
    /*
    -1.62
    h
    -1.61
    up
    -1.61
     și
    -1.60
    ?’
    -1.59
        
    -1.58
     olhando
    -1.55
     -,
    -1.55
    POSITIVE LOGITS
     mere
    1.75
    ナイキ
    1.74
     den
    1.68
    —
    1.66
    şört
    1.64
     Hauses
    1.56
     детстве
    1.56
    凌晨
    1.51
    ߰
    1.50
    Бил
    1.48
    Activations Density 0.001%

    No Known Activations