© 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
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 5877
    Prev
    Next
    INDEX
    Explanations

    workflow automation analysis

    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
    らに
    1.56
    га
    1.52
    اس
    1.52
    ди
    1.42
    ний
    1.38
     proteg
    1.38
    彡
    1.35
     desenvolv
    1.34
    itization
    1.34
    ma
    1.33
    POSITIVE LOGITS
    sburg
    1.77
    ли
    1.72
    𝗚
    1.66
    SECONDS
    1.64
    <unused2037>
    1.59
    CPM
    1.56
    𝗗
    1.53
    自定义
    1.51
    ન
    1.50
    DCT
    1.49
    Activations Density 0.019%

    No Known Activations