© 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. 6900
    Prev
    Next
    INDEX
    Explanations

    definitions and explanations

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

    specifying aspects of things

    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
     رغم
    0.44
    それでも
    0.44
     spite
    0.39
    )].
    0.39
    总之
    0.38
     şimdi
    0.38
     heretofore
    0.38
     dubious
    0.38
     malgré
    0.38
    마
    0.37
    POSITIVE LOGITS
     Usually
    0.63
     usually
    0.62
     AKA
    0.57
     Therefore
    0.56
     называется
    0.56
     அதாவது
    0.56
     biasanya
    0.55
     म्हणजेच
    0.55
     therefore
    0.54
     असतो
    0.54
    Activations Density 0.108%

    No Known Activations