© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 10311
    Prev
    Next
    INDEX
    Explanations

    humanitarian aid and crises

    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_16k_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
    Mard
    0.42
    InputElement
    0.42
     ቲ
    0.42
    সজ্জিত
    0.41
    执法
    0.40
     desiring
    0.38
    选择了
    0.38
    奋斗
    0.38
    🏤
    0.38
     حصے
    0.38
    POSITIVE LOGITS
     humanitarian
    0.98
     Humanitarian
    0.93
     disaster
    0.68
     Disaster
    0.63
     Crisis
    0.61
     refugee
    0.60
     நிவார
    0.59
     famine
    0.59
     catastrophe
    0.58
     UNHCR
    0.58
    Activations Density 0.070%

    No Known Activations