© 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. 57161
    Prev
    Next
    INDEX
    Explanations

    humanitarian aid operations

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

    humanitarian aid logistics

    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
     পরিবর্ত
    0.44
     przech
    0.43
    KeyState
    0.42
     ል
    0.41
    的企业
    0.41
    ousedown
    0.40
    꼈
    0.40
    ូន
    0.40
     Ignition
    0.40
    ൩
    0.40
    POSITIVE LOGITS
     Humanitarian
    1.01
     humanitarian
    0.96
     ICRC
    0.65
     UNHCR
    0.58
     NGO
    0.57
     நிவார
    0.57
     logistical
    0.54
     convoy
    0.53
     Logistics
    0.53
     USAID
    0.51
    Activations Density 0.058%

    No Known Activations