© 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. 41-GEMMASCOPE-2-RES-65K
    7. 1508
    Prev
    Next
    INDEX
    Explanations

    listing components

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_41_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
    そこ
    0.54
    ッサージ
    0.53
    ουν
    0.52
     Bur
    0.52
    μαι
    0.51
    迦
    0.51
    Mead
    0.49
    咁
    0.49
     poisoning
    0.48
     tell
    0.48
    POSITIVE LOGITS
    前的
    0.58
     мог
    0.57
     ellipt
    0.56
     EMP
    0.54
    텝
    0.54
     stands
    0.54
     могли
    0.53
     кораб
    0.52
     सिम
    0.51
     înainte
    0.51
    Activations Density 0.000%

    No Known Activations