© 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
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 7582
    Prev
    Next
    INDEX
    Explanations

    University affiliation

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

    university names

    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
     McGill
    0.48
     Tufts
    0.46
     NYU
    0.44
     Cornell
    0.42
     विश्वविद्यालयों
    0.41
     UCLA
    0.41
     Rutgers
    0.41
     界
    0.40
     rooms
    0.39
    Cornell
    0.39
    POSITIVE LOGITS
     Libraries
    0.63
     School
    0.63
     Graduate
    0.60
     Bookstore
    0.59
     Library
    0.58
    附属
    0.58
     LIBRARY
    0.55
     Faculty
    0.54
     graduate
    0.54
     Alumni
    0.51
    Activations Density 0.129%

    No Known Activations