© 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. 7111
    Prev
    Next
    INDEX
    Explanations

    p.m. times

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

    time expressions

    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
     answer
    0.48
    m
    0.45
     Anonymous
    0.45
    ANSWER
    0.43
     replies
    0.43
     answers
    0.42
     later
    0.42
    하려고
    0.42
     الله
    0.41
     জবাবে
    0.41
    POSITIVE LOGITS
    YAML
    0.42
     قیام
    0.39
    যোগ
    0.39
    Swipe
    0.39
     किफ
    0.38
    罾
    0.38
    Goods
    0.37
     Casting
    0.37
    ່າຍ
    0.37
     വ്യ
    0.37
    Activations Density 0.000%

    No Known Activations