© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 2403
    Prev
    Next
    INDEX
    Explanations

    general principles or definitions

    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
    叢
    0.57
     Antworten
    0.55
     เค
    0.54
    Видео
    0.54
    siehe
    0.54
     ไหม
    0.54
    Eu
    0.54
    𒋗
    0.54
     Videos
    0.53
     heapq
    0.53
    POSITIVE LOGITS
    亘
    0.59
     Miłos
    0.54
    ती
    0.53
    cemic
    0.53
    tha
    0.50
     स्नान
    0.50
    Maintain
    0.50
    oit
    0.50
    高く
    0.50
    configure
    0.49
    Activations Density 0.000%

    No Known Activations