© 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. 4443
    Prev
    Next
    INDEX
    Explanations

    social situation nouns

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

    feeling and sensation

    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
     locales
    0.43
    ("|"+"
    0.41
     kompon
    0.40
     ভারতীয়রা
    0.38
     heralded
    0.38
    descriptors
    0.38
    ফুদ্দিন
    0.38
    敝
    0.38
     folks
    0.37
     yep
    0.37
    POSITIVE LOGITS
     bruise
    0.63
     awkward
    0.62
     kiss
    0.61
     sudden
    0.58
     পরিস্থিতি
    0.57
     situation
    0.57
     conversation
    0.57
     confession
    0.57
     girl
    0.56
     confrontation
    0.56
    Activations Density 0.068%

    No Known Activations