© 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. 7847
    Prev
    Next
    INDEX
    Explanations

    Stephen followed by surname

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

    Stephen/Steven/Steve followed by last name

    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
    🧨
    0.42
    струк
    0.42
    defining
    0.41
    ைக்கு
    0.40
    娅
    0.38
     complying
    0.36
    newsletter
    0.36
    subplots
    0.35
    Structure
    0.35
    硐
    0.35
    POSITIVE LOGITS
     Hawking
    0.61
     Stephen
    0.57
    Stephen
    0.54
     Spielberg
    0.54
     Decatur
    0.46
     ә
    0.42
     Ceci
    0.42
     Colbert
    0.40
     Sond
    0.40
    ie
    0.39
    Activations Density 0.015%

    No Known Activations