© 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. 51306
    Prev
    Next
    INDEX
    Explanations

    cities and administrative levels

    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
    鰍
    0.51
     collabor
    0.47
     semilla
    0.44
     सहयोगी
    0.44
     transmutation
    0.44
     همکاری
    0.44
     paura
    0.44
     sympathies
    0.44
     modifica
    0.44
     caffè
    0.44
    POSITIVE LOGITS
    cante
    0.46
    uffled
    0.46
     മറ്റ
    0.45
    dp
    0.44
     ഉണ്ടായി
    0.44
    d
    0.44
    zäh
    0.43
    dip
    0.43
    kd
    0.42
    direct
    0.42
    Activations Density 0.008%

    No Known Activations