© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 112381
    Prev
    Next
    INDEX
    Explanations

    mind you / me asking

    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
    Initializable
    -1.73
    bitol
    -1.62
    izzazioni
    -1.61
    élé
    -1.57
    ,’
    -1.55
    athus
    -1.55
     (‘
    -1.54
     hermosos
    -1.54
    ?’
    -1.51
     wyposaż
    -1.51
    POSITIVE LOGITS
    ahhh
    1.91
    you
    1.85
     utop
    1.80
    笵
    1.78
     ortodo
    1.71
    鸶
    1.66
    鸲
    1.65
    葙
    1.64
     própri
    1.62
    发现了
    1.61
    Activations Density 0.004%

    No Known Activations