© 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. 779
    Prev
    Next
    INDEX
    Explanations

    don't bother

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

    don't hurt me

    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
     onTap
    0.44
    不安定
    0.42
     सूफ़ी
    0.39
    -$
    0.39
    ïs
    0.39
     раду
    0.38
     diverging
    0.37
    
    0.37
     Quiet
    0.37
     officiating
    0.37
    POSITIVE LOGITS
     bother
    0.57
     hassle
    0.55
     bothered
    0.51
     hurt
    0.50
     trouble
    0.48
     bothering
    0.46
     detain
    0.43
     bothers
    0.43
     hygienic
    0.43
     hindrance
    0.42
    Activations Density 0.003%

    No Known Activations