© 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. 40-GEMMASCOPE-2-RES-16K
    7. 9460
    Prev
    Next
    INDEX
    Explanations

    EU project consortium

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

    partnership consortia international projects

    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_40_width_16k_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
    劃
    0.42
     అమె
    0.41
     Sponsorship
    0.41
     Maddox
    0.40
     عق
    0.40
     overheard
    0.40
     Vaughn
    0.38
     作
    0.38
     ungraded
    0.38
    をしている
    0.38
    POSITIVE LOGITS
     consortium
    0.98
     partners
    0.78
     consort
    0.77
     Consortium
    0.76
     Erasmus
    0.76
     project
    0.70
     projekt
    0.68
     transnational
    0.68
     EU
    0.68
     progetto
    0.68
    Activations Density 0.241%

    No Known Activations