© 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. 194940
    Prev
    Next
    INDEX
    Explanations

    Caspian Sea, global climate, part series

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

    as/proxy

    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
    つまり
    0.51
     あなた
    0.51
     существуют
    0.51
     істо
    0.50
    かっこ
    0.49
     موضوع
    0.48
    かわいい
    0.48
     ਯ
    0.48
     ま
    0.48
    politics
    0.48
    POSITIVE LOGITS
     Bacteria
    0.43
     Kejriwal
    0.43
     pyl
    0.43
     Ment
    0.41
    乩
    0.41
     bar
    0.41
     Sessions
    0.41
     Medina
    0.41
     Committees
    0.41
     Developer
    0.41
    Activations Density 0.001%

    No Known Activations