© 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. 128683
    Prev
    Next
    INDEX
    Explanations

    voting, elections, municipal, neighborhood

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

    local holidays and aesthetics

    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
     ergonom
    0.47
     eukary
    0.47
     océ
    0.46
    🛫
    0.46
     ovip
    0.45
     has
    0.45
     envisaged
    0.45
     hopped
    0.44
     اروپا
    0.43
     fasted
    0.43
    POSITIVE LOGITS
    Votes
    0.59
     คะแนน
    0.54
    Municipal
    0.50
     뽑
    0.48
     खारिज
    0.47
     निवडणूक
    0.47
     मतदार
    0.46
    County
    0.46
    Neighborhood
    0.46
     항목
    0.46
    Activations Density 0.000%

    No Known Activations