© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 132648
    Prev
    Next
    INDEX
    Explanations

    forms of 'to be'

    np_acts-logits-general · gemini-2.5-flash-lite

    is or am followed by description

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     számos
    0.45
     Уи
    0.43
     каким
    0.42
    莠
    0.41
     దాని
    0.41
    יים
    0.41
     நாட்கள்
    0.40
    下标
    0.40
     baz
    0.39
    这篇文章
    0.39
    POSITIVE LOGITS
    idental
    0.43
     very
    0.43
    応援
    0.43
     true
    0.42
    ｉ
    0.40
    do
    0.39
    ider
    0.39
    forme
    0.39
    ｒ
    0.39
     contented
    0.39
    Activations Density 0.137%

    No Known Activations