© 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. 70232
    Prev
    Next
    INDEX
    Explanations

    Android Oreo

    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
    idious
    -0.98
    ,#
    -0.97
    =\"
    -0.94
    vák
    -0.90
     charged
    -0.90
    достатки
    -0.88
    \]
    -0.88
    ！！！”
    -0.87
    eclared
    -0.85
    totalSupply
    -0.85
    POSITIVE LOGITS
     shitty
    0.97
     людей
    0.97
     Amongst
    0.95
     различных
    0.94
     berbagai
    0.93
     downsides
    0.91
     meisjes
    0.89
     despues
    0.86
    layın
    0.84
     allerlei
    0.84
    Activations Density 0.004%

    No Known Activations