© 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. 17075
    Prev
    Next
    INDEX
    Explanations

    plural nouns ending in s or ers

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

    my core principles

    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
     wills
    0.43
     profiles
    0.42
    oches
    0.40
     नामों
    0.40
     lifestyles
    0.40
     сами
    0.40
     самих
    0.38
     –
    0.38
    本人
    0.38
     biographies
    0.38
    POSITIVE LOGITS
     own
    0.83
    own
    0.60
     newest
    0.56
     মতো
    0.54
     பெரும்பாலான
    0.54
     todays
    0.54
     wildest
    0.53
    Thats
    0.53
     einzige
    0.52
    Own
    0.52
    Activations Density 0.082%

    No Known Activations