© 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. 22873
    Prev
    Next
    INDEX
    Explanations

    government ministers and secretaries

    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
    湫
    0.45
     ofx
    0.45
     给
    0.43
    计算机
    0.43
     자체
    0.43
     Tahoma
    0.42
     형태
    0.42
    𝑃
    0.42
    ిత
    0.42
    耶稣
    0.42
    POSITIVE LOGITS
     ministerial
    0.97
     Minister
    0.95
     وزير
    0.95
     minister
    0.94
     Ministerial
    0.89
     Ministers
    0.86
    Minister
    0.86
     ministers
    0.84
     ministre
    0.84
    minister
    0.81
    Activations Density 0.011%

    No Known Activations