© 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
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 4649
    Prev
    Next
    INDEX
    Explanations

    starts words in multiple scripts

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

    Italian, Spanish, Russian, Malayalam, Tagalog

    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
    essional
    0.41
    itys
    0.41
    itate
    0.40
    s
    0.40
    ids
    0.39
    APE
    0.39
    ↵
    0.39
    mm
    0.39
    THERS
    0.39
    .
    0.39
    POSITIVE LOGITS
     ಬಹಳ
    0.52
     በጣም
    0.50
    ധികം
    0.48
     പിന്നീ
    0.44
     ඉතා
    0.44
     እንዲሁ
    0.42
     весьма
    0.42
     ശക്ത
    0.41
     никаких
    0.41
     एकदम
    0.40
    Activations Density 0.002%

    No Known Activations