© 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. 38285
    Prev
    Next
    INDEX
    Explanations

    dieting laxative effect

    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
     jedi
    -1.06
    Jedi
    -1.04
    Tro
    -1.02
    DFA
    -0.98
     Boba
    -0.97
     Jedi
    -0.94
    ״
    -0.93
     kilo
    -0.90
     />
    -0.90
    Sushi
    -0.90
    POSITIVE LOGITS
     NEET
    1.09
     splet
    0.99
     cooking
    0.97
     začet
    0.96
    smartphone
    0.95
     ayak
    0.93
    reebok
    0.91
    Lutz
    0.91
    存于互联网档案馆
    0.91
    不良
    0.91
    Activations Density 0.036%

    No Known Activations