© 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. 4219
    Prev
    Next
    INDEX
    Explanations

    ship related things

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

    obstacle, Volatility, park, consent, Thesis

    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
     hypothalamic
    0.41
     cytoplasmic
    0.39
     cytosolic
    0.38
     convolutional
    0.38
     interfacial
    0.38
    脘
    0.38
     anodic
    0.36
     microbial
    0.36
     apical
    0.36
     subordinated
    0.35
    POSITIVE LOGITS
    ablemente
    0.44
     shipwreck
    0.44
    であろう
    0.44
    णारा
    0.43
    anagram
    0.42
    熟悉的
    0.42
    timezone
    0.42
     എല്ലാം
    0.42
    ઁ
    0.41
    <unused544>
    0.41
    Activations Density 0.373%

    No Known Activations