© 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. 4635
    Prev
    Next
    INDEX
    Explanations

    male names

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

    names following "by" or "aka"

    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
    </em>
    0.51
     größ
    0.40
    收益
    0.40
    Pues
    0.39
    dumps
    0.39
    Brexit
    0.38
    स्‍त
    0.38
     संस्क
    0.38
    貰
    0.38
     затруд
    0.37
    POSITIVE LOGITS
     Joe
    0.62
     Mike
    0.54
     Bob
    0.54
     Jimmy
    0.54
     Kate
    0.53
     Tony
    0.52
     Pete
    0.52
     Robert
    0.51
     Abby
    0.50
     Kevin
    0.50
    Activations Density 0.346%

    No Known Activations