© 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-65K
    7. 46358
    Prev
    Next
    INDEX
    Explanations

    Haiti crisis

    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_65k_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
    Соцмережа
    0.47
     comorbidities
    0.47
    炰
    0.45
     vestibular
    0.44
     painkillers
    0.44
    एको
    0.44
    采集
    0.44
    邕
    0.43
     autosomal
    0.43
     त्रिदेव
    0.43
    POSITIVE LOGITS
    ld
    0.60
    s
    0.59
    ng
    0.54
    rm
    0.52
    ↵
    0.51
    sink
    0.51
    old
    0.50
    anh
    0.49
    с
    0.49
    nu
    0.48
    Activations Density 0.003%

    No Known Activations