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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 16883
    Prev
    Next
    INDEX
    Explanations

    academic degrees and fields

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

    B.Sc, B.A., B.S. degrees

    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
    삭제
    0.40
     specialties
    0.40
     Selatan
    0.40
     돈
    0.39
     jinak
    0.39
     جي
    0.38
    Satellite
    0.38
     NOR
    0.38
    тари
    0.38
    💰
    0.38
    POSITIVE LOGITS
    Phil
    0.56
    litt
    0.52
    Sc
    0.51
    Arts
    0.50
     Litt
    0.49
    phil
    0.49
     Arts
    0.48
     arts
    0.47
    Litt
    0.47
     Phil
    0.46
    Activations Density 0.027%

    No Known Activations