© 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. 240549
    Prev
    Next
    INDEX
    Explanations

    role in finance and government

    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
    馁
    0.54
    쐞
    0.52
     बड़
    0.50
    黎
    0.50
    óp
    0.49
    慫
    0.49
     Piano
    0.48
    获得了
    0.47
     Lattice
    0.47
    阿里
    0.47
    POSITIVE LOGITS
     deputies
    0.52
     jurisdictions
    0.52
     flee
    0.50
     scalars
    0.50
    >
    0.50
     compromise
    0.49
     compromises
    0.48
     reprieve
    0.48
     committees
    0.48
    tive
    0.47
    Activations Density 0.000%

    No Known Activations