© 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. 1623
    Prev
    Next
    INDEX
    Explanations

    traditional

    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
    ibhav
    0.46
    呟
    0.46
     আনন্দের
    0.44
     ocas
    0.43
     겸
    0.43
    dessous
    0.42
    वणे
    0.42
    ಕ್ರ
    0.42
    佚
    0.41
     ungraded
    0.40
    POSITIVE LOGITS
     traditional
    2.48
     conventional
    2.47
     тради
    2.25
    traditional
    2.25
    传统
    2.23
    conventional
    2.23
    传统的
    2.23
    Traditional
    2.20
    Conventional
    2.19
     tradizionale
    2.14
    Activations Density 1.131%

    No Known Activations