© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 5078
    Prev
    Next
    INDEX
    Explanations

    durations in years and months

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

    multilingual content or code-switching

    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
    five
    0.44
    formula
    0.42
    かを
    0.42
    Formula
    0.41
    fifty
    0.40
    anju
    0.40
    ঝো
    0.39
    菩
    0.39
    نګ
    0.38
    FIVE
    0.38
    POSITIVE LOGITS
     PLAT
    0.44
    isement
    0.43
     Advertisement
    0.41
     bulan
    0.40
    Advertisement
    0.40
     Months
    0.40
     Už
    0.40
    igion
    0.38
     Bulan
    0.38
     subscribers
    0.38
    Activations Density 0.000%

    No Known Activations