© 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-65K
    7. 49253
    Prev
    Next
    INDEX
    Explanations

    function arguments keyword

    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
    {
    0.58
    می
    0.52
     为
    0.51
    ن
    0.48
    ઈ
    0.48
    detailID
    0.47
    ک
    0.46
     चित्रित
    0.46
     为了
    0.45
     مسجد
    0.45
    POSITIVE LOGITS
    z
    0.67
    ethe
    0.60
     The
    0.56
    ومة
    0.52
    zell
    0.50
    zellen
    0.49
    ंतर
    0.46
     or
    0.46
    The
    0.45
    ise
    0.44
    Activations Density 0.098%

    No Known Activations