© 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. 208707
    Prev
    Next
    INDEX
    Explanations

    I followed by a verb

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

    analyzing human aesthetics and cognition

    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
    嫚
    0.44
    好像
    0.43
    出荷
    0.43
     पार्टी
    0.41
    嘅
    0.41
    INO
    0.40
     एकदम
    0.40
    他們的
    0.40
    shima
    0.39
     ड
    0.39
    POSITIVE LOGITS
     physicians
    0.48
     autonomous
    0.47
     generational
    0.47
     computational
    0.45
     genomics
    0.45
     researchers
    0.44
     physician
    0.44
     aging
    0.44
     computation
    0.43
     scientists
    0.43
    Activations Density 0.049%

    No Known Activations