© 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. 31-GEMMASCOPE-2-RES-262K
    7. 20828
    Prev
    Next
    INDEX
    Explanations

    head of government roles

    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_31_width_262k_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
    CriteriaUtils
    0.49
    𝘻
    0.48
     új
    0.47
     melhorar
    0.46
    蔡
    0.46
    ጷ
    0.45
     migliorare
    0.45
     lágrimas
    0.45
    奨
    0.44
     Contreras
    0.44
    POSITIVE LOGITS
     subordinate
    0.59
     monarchy
    0.57
    liament
    0.56
     აღმასრულებელი
    0.55
     functions
    0.54
     executive
    0.54
    Functions
    0.54
     subordination
    0.54
     duties
    0.53
     elected
    0.52
    Activations Density 0.064%

    No Known Activations