© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 16115
    Prev
    Next
    INDEX
    Explanations

    third person actions or states

    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
    あなたは
    0.70
    You
    0.68
     vous
    0.64
     yourself
    0.63
     você
    0.61
    Você
    0.60
     You
    0.59
     你
    0.59
    当你
    0.59
    you
    0.58
    POSITIVE LOGITS
    让她
    0.83
    讓他
    0.82
    她
    0.81
     ему
    0.79
     she
    0.78
    让他
    0.76
     அவருக்கு
    0.74
    គាត់
    0.73
    她在
    0.73
    她说
    0.73
    Activations Density 0.156%

    No Known Activations