© 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. 8231
    Prev
    Next
    INDEX
    Explanations

    Bronston, KY types of

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

    mathematical expressions with units and exponents

    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
    တ်
    0.42
     المختلف
    0.39
    reen
    0.39
    —
    0.39
     «
    0.38
    dealing
    0.38
    myfile
    0.38
     maga
    0.38
    㚘
    0.37
     éta
    0.36
    POSITIVE LOGITS
     cytokine
    0.49
     diploid
    0.43
     Inhib
    0.43
     GSK
    0.42
     Selle
    0.42
     selle
    0.42
     inhibition
    0.42
     cytokines
    0.42
     Inhibition
    0.41
    нів
    0.40
    Activations Density 0.033%

    No Known Activations