© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 15091
    Prev
    Next
    INDEX
    Explanations

    table separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-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
     দুর্
    0.59
    act
    0.56
     sequential
    0.55
     optimal
    0.54
    错误的
    0.53
    ຳ
    0.53
    适应
    0.53
    %、
    0.53
    ある
    0.52
     வரைய
    0.52
    POSITIVE LOGITS
    perclip
    0.63
     compreensão
    0.61
    лас
    0.59
     Antônio
    0.59
     quím
    0.58
    ṇa
    0.57
     молоко
    0.57
    URACY
    0.56
    ificante
    0.56
     darbo
    0.56
    Activations Density 0.118%

    No Known Activations