© 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. 5312
    Prev
    Next
    INDEX
    Explanations

    public

    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
     무엇
    0.56
     src
    0.54
     čemu
    0.53
     Crea
    0.53
    Ნ
    0.52
     what
    0.51
    层次
    0.51
     ContentView
    0.50
     couleurs
    0.50
     व्हाट
    0.50
    POSITIVE LOGITS
    punten
    0.63
    кор
    0.62
    ال
    0.57
    ্যাপ
    0.57
    勺
    0.55
    ᧐
    0.55
    роки
    0.54
     diperlukan
    0.54
    ്യാപ
    0.54
    provided
    0.53
    Activations Density 0.018%

    No Known Activations