© 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. 7260
    Prev
    Next
    INDEX
    Explanations

    administrative and financial processes

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

    current status or challenges

    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
    连接
    0.64
    饮食
    0.57
     应用
    0.57
    电池
    0.57
    无线
    0.55
     对于
    0.54
     음
    0.54
     texId
    0.52
     给
    0.52
     คุณ
    0.51
    POSITIVE LOGITS
     bureaucratic
    0.75
     budgetary
    0.71
    financ
    0.70
    crisis
    0.68
    fiscal
    0.66
    funding
    0.66
     hurdles
    0.64
     bureaucracy
    0.64
    administrative
    0.64
     administrat
    0.63
    Activations Density 0.194%

    No Known Activations