© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 9142
    Prev
    Next
    INDEX
    Explanations

    specific terms or phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_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
     DWORD
    0.40
    rowned
    0.39
     Süden
    0.37
     ጭ
    0.36
     Bunu
    0.36
     Tb
    0.35
    ប់
    0.35
    RIBUT
    0.34
    ayside
    0.34
     তাঁরা
    0.33
    POSITIVE LOGITS
     selaku
    0.98
    ซึ่ง
    0.86
     czyli
    0.80
    which
    0.77
    ،
    0.74
     which
    0.73
     जोकि
    0.71
     iaitu
    0.71
     यानी
    0.70
     नामक
    0.70
    Activations Density 0.227%

    No Known Activations