© 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. 94671
    Prev
    Next
    INDEX
    Explanations

    political entities and concepts

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

    movement or direction

    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
    la
    0.50
    i
    0.49
    u
    0.49
     old
    0.46
     Metallic
    0.46
     oil
    0.46
     Central
    0.46
     Synthetic
    0.46
     belge
    0.45
     metal
    0.45
    POSITIVE LOGITS
     السيد
    0.54
     আবদুল
    0.53
     على
    0.51
    秏
    0.50
    的项目
    0.50
    髗
    0.49
    妈妈
    0.48
     controvers
    0.48
    న్
    0.48
     চেয়ার
    0.47
    Activations Density 0.001%

    No Known Activations