© 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. 31-GEMMASCOPE-2-RES-16K
    4. 5832
    Prev
    Next
    INDEX
    Explanations

    information and system attributes

    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_31_width_16k_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
    は見
    0.79
    もあり
    0.69
    though
    0.68
    ಿತ್ತು
    0.68
    は
    0.64
    도
    0.64
    вается
    0.63
    もあります
    0.62
     ఉంది
    0.59
    まで
    0.59
    POSITIVE LOGITS
     యొక్క
    1.34
    信息的
    1.26
    ஸின்
    1.23
    使用的
    1.20
    数据的
    1.20
    的一個
    1.19
    工作的
    1.19
     的
    1.17
    ாவின்
    1.17
    存在的
    1.16
    Activations Density 0.049%

    No Known Activations