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

    Neuronpedia

    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. 55891
    Prev
    Next
    INDEX
    Explanations

    uncertainty, doubt, debated

    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
    다
    0.51
    inien
    0.49
    竰
    0.49
    ষা
    0.48
    ྐ
    0.48
    שׁ
    0.47
    滘
    0.47
     다양한
    0.46
    ש
    0.46
    ಸೆ
    0.46
    POSITIVE LOGITS
     dubbio
    0.81
     doute
    0.77
     doubted
    0.76
     uncertain
    0.74
     doubtful
    0.73
     doubt
    0.72
     dúvida
    0.66
     doubting
    0.65
     einde
    0.64
     doubts
    0.64
    Activations Density 0.087%

    No Known Activations