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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 17824
    Prev
    Next
    INDEX
    Explanations

    historical and descriptive terms

    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_262k_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
     sver
    0.48
     tận
    0.47
    staticmethod
    0.46
     canada
    0.46
     fong
    0.46
     그다
    0.45
    length
    0.44
    =>
    0.44
     taka
    0.43
    olja
    0.43
    POSITIVE LOGITS
    یش
    0.45
    ın
    0.44
    ée
    0.43
    کومت
    0.43
     boxe
    0.43
    ض
    0.41
    ന്നാ
    0.41
    ید
    0.41
    рю
    0.41
     desesper
    0.41
    Activations Density 0.002%

    No Known Activations