© 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
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 6678
    Prev
    Next
    INDEX
    Explanations

    sympathy and condolences

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

    sending greetings and apologies

    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
     🥰
    0.57
    🥰
    0.48
     remerc
    0.48
     💕
    0.48
     😍
    0.47
     importantly
    0.47
     😘
    0.45
     laughter
    0.44
     graças
    0.44
     ❤
    0.44
    POSITIVE LOGITS
    sorry
    1.07
     sorry
    1.03
    Sorry
    0.97
     Sorry
    0.97
     Cond
    0.67
    SOR
    0.66
    Cond
    0.66
    cond
    0.63
     deepest
    0.63
    Offering
    0.61
    Activations Density 0.015%

    No Known Activations