© 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. 4580
    Prev
    Next
    INDEX
    Explanations

    closing salutations and superlatives

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

    closing salutations

    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
    WELL
    0.51
    THANK
    0.50
    HAPPY
    0.46
     THANK
    0.44
     ESPE
    0.43
     OH
    0.42
     PLEASE
    0.42
     💞
    0.42
    WELCOME
    0.42
    💞
    0.41
    POSITIVE LOGITS
     regards
    1.99
    Regards
    1.97
     Regards
    1.94
     regard
    1.55
    Cheers
    1.27
    Sincerely
    1.14
     Cheers
    1.11
     cheers
    1.09
     regarded
    1.08
    Saludos
    1.02
    Activations Density 0.114%

    No Known Activations