© 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. 117936
    Prev
    Next
    INDEX
    Explanations

    or avoid professional medical advice

    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
    кульп
    -0.83
     blatantly
    -0.82
    バイル
    -0.82
    hésite
    -0.80
    yentes
    -0.79
    ઑ
    -0.79
    geox
    -0.79
     exquisitely
    -0.78
     extravagant
    -0.78
     проб
    -0.78
    POSITIVE LOGITS
    lation
    0.90
     нашего
    0.86
    あんまり
    0.85
    ERON
    0.85
     mortem
    0.84
     нашей
    0.84
     nossos
    0.83
    aken
    0.83
    gade
    0.82
    iedenen
    0.82
    Activations Density 0.009%

    No Known Activations