© 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-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 55568
    Prev
    Next
    INDEX
    Explanations

    geographic borders and neighbors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     zentrale
    0.44
    нома
    0.42
     центра
    0.40
     தாம
    0.40
    졸
    0.39
     الحاج
    0.38
    卆
    0.37
    आपने
    0.37
    婳
    0.36
     સૌ
    0.36
    POSITIVE LOGITS
     sharing
    0.63
     bounded
    0.60
     bounding
    0.59
     neighbors
    0.57
     touches
    0.55
     bordered
    0.53
     neighbours
    0.52
     bordering
    0.52
     Sharing
    0.51
     neighbor
    0.51
    Activations Density 0.047%

    No Known Activations