© 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. 12-GEMMASCOPE-2-RES-262K
    7. 30616
    Prev
    Next
    INDEX
    Explanations

    Tensor product, consists of, design for, presenting tumor, yield from

    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_12_width_262k_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
    可以
    0.95
    𝓈
    0.95
    о
    0.94
     può
    0.93
    状态
    0.89
     basados
    0.89
    就会
    0.88
     toutes
    0.88
    最优
    0.87
    emaker
    0.87
    POSITIVE LOGITS
    ToServer
    0.87
    Stretch
    0.86
    ک
    0.86
    Ty
    0.84
     Shares
    0.80
    ُ
    0.80
     către
    0.79
     Toen
    0.79
    yati
    0.78
    pubescens
    0.77
    Activations Density 0.000%

    No Known Activations