© 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. 41-GEMMASCOPE-2-RES-262K
    7. 1536
    Prev
    Next
    INDEX
    Explanations

    forms of address

    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_all/layer_41_width_262k_l0_big
    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
    ⺈
    0.47
    ார்க்க
    0.46
     affaire
    0.46
     njima
    0.44
     বহন
    0.44
    ktional
    0.43
     wysoko
    0.42
    itate
    0.42
     eux
    0.42
    繁忙時間服務
    0.42
    POSITIVE LOGITS
    님
    0.57
     ሆ
    0.51
     don
    0.51
     thank
    0.51
     спасибо
    0.50
     你
    0.49
     didn
    0.49
     forgive
    0.48
     나는
    0.48
    你怎么
    0.48
    Activations Density 0.014%

    No Known Activations