© 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. 31-GEMMASCOPE-2-RES-16K
    7. 3933
    Prev
    Next
    INDEX
    Explanations

    model responses

    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
     menggambarkan
    0.57
     ब्लॉग
    0.56
     اکثر
    0.56
     opcion
    0.56
     menampilkan
    0.55
     mempelajari
    0.55
     az
    0.55
    勹
    0.55
     toepassing
    0.54
     wymien
    0.54
    POSITIVE LOGITS
    Li
    0.65
    Mill
    0.64
    Mgr
    0.64
    ((\
    0.63
    Menurut
    0.62
    Det
    0.61
    See
    0.61
    Pr
    0.61
    Lond
    0.61
    Gloria
    0.60
    Activations Density 0.029%

    No Known Activations