© 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. 43330
    Prev
    Next
    INDEX
    Explanations

    client routing statement practice minute

    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
     quelconque
    1.43
    stmt
    1.39
    不过
    1.39
     peroneal
    1.37
    Autres
    1.36
    어요
    1.34
     randomNumber
    1.33
    ک
    1.29
    શ
    1.29
    والفقار
    1.28
    POSITIVE LOGITS
    ্লাহ
    1.71
    ्या
    1.69
    с
    1.63
     canad
    1.55
    癀
    1.52
    ारा
    1.51
    𝘺
    1.51
    ز
    1.48
    ió
    1.47
    ف
    1.46
    Activations Density 0.001%

    No Known Activations