© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 35668
    Prev
    Next
    INDEX
    Explanations

    previous examples and company information

    np_acts-logits-general · gemini-2.5-flash-lite

    circulates blood to organs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    컨
    0.45
    decompose
    0.44
    фт
    0.44
    קת
    0.44
    メル
    0.43
     purify
    0.43
     cib
    0.43
    👯
    0.43
    ुट
    0.43
     Bastian
    0.42
    POSITIVE LOGITS
     Other
    0.50
     Makes
    0.46
     таксама
    0.46
     മറ്റ്
    0.45
     також
    0.45
     Также
    0.45
     также
    0.44
     Though
    0.43
     আপাত
    0.42
     Note
    0.42
    Activations Density 0.001%

    No Known Activations