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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 1579
    Prev
    Next
    INDEX
    Explanations

    of them, us, these

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

    referring to multiple options

    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_53_width_65k_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
     该
    0.45
     }=\
    0.40
     unele
    0.39
     बरे
    0.38
    και
    0.38
    according
    0.38
    的這個
    0.37
    })}{
    0.36
    ой
    0.36
     някои
    0.36
    POSITIVE LOGITS
     them
    1.14
     those
    0.85
    them
    0.85
     us
    0.84
     these
    0.84
     них
    0.78
     whom
    0.75
     THEM
    0.72
     देम
    0.70
     our
    0.63
    Activations Density 0.279%

    No Known Activations