© 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. 221577
    Prev
    Next
    INDEX
    Explanations

    European election or political terms

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

    election, presentation, exoneration

    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
    nian
    0.50
    inge
    0.45
    ensitive
    0.43
    ície
    0.42
    난
    0.41
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.41
    zv
    0.41
    maa
    0.41
    .
    0.40
    ۔
    0.40
    POSITIVE LOGITS
     errori
    0.51
     त्रुट
    0.50
     गुणों
    0.49
     चुनाव
    0.49
    廸
    0.48
     election
    0.48
     pursue
    0.48
     पात्रता
    0.47
     supremacy
    0.47
     présenté
    0.47
    Activations Density 0.001%

    No Known Activations