Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 4794
    Prev
    Next
    INDEX
    Explanations

    context for "you"

    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
     unanticipated
    0.50
     bestowed
    0.48
     unforeseen
    0.47
     acquitted
    0.47
     adversely
    0.46
    최
    0.46
     unsettling
    0.45
     perturbed
    0.44
     perceiving
    0.44
     victorious
    0.43
    POSITIVE LOGITS
     bạn
    0.76
     youre
    0.66
     तुम्हाला
    0.65
    you
    0.64
     you
    0.62
     మీరు
    0.62
     আপনি
    0.61
     你
    0.61
     跟
    0.59
     youll
    0.58
    Activations Density 0.088%

    No Known Activations