© 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. 8650
    Prev
    Next
    INDEX
    Explanations

    they followed by a verb

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

    they have

    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
     sám
    0.54
     сам
    0.53
     самому
    0.48
     নিজেকে
    0.47
     l
    0.47
     himself
    0.47
     रोकता
    0.46
     vzdu
    0.44
     ລ
    0.44
     способен
    0.44
    POSITIVE LOGITS
     themselves
    1.02
    Their
    0.97
    他們的
    0.94
    他们的
    0.92
    They
    0.89
    他們
    0.88
     Their
    0.88
     they
    0.84
     their
    0.84
    their
    0.81
    Activations Density 0.316%

    No Known Activations