© 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. 4250
    Prev
    Next
    INDEX
    Explanations

    person names

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

    names of people and their associated items

    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
     erad
    0.37
    куляр
    0.36
     شاء
    0.35
    毉
    0.35
     anisot
    0.35
    явля
    0.34
     Украине
    0.34
     infest
    0.34
     kinet
    0.34
     കേരള
    0.34
    POSITIVE LOGITS
     “
    0.38
    it
    0.33
    ur
    0.31
    us
    0.31
    award
    0.31
     ‘
    0.31
     bizony
    0.30
     \"
    0.30
     Som
    0.30
    ART
    0.30
    Activations Density 0.016%

    No Known Activations