© 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. 7411
    Prev
    Next
    INDEX
    Explanations

    lamp

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

    lamp

    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
     ഭൂ
    0.42
    xl
    0.41
     نحن
    0.39
    וט
    0.39
    ह्म
    0.39
     ادا
    0.38
    细
    0.38
    픽
    0.38
    wu
    0.37
    redu
    0.37
    POSITIVE LOGITS
     lamp
    0.58
     Lamp
    0.52
    lamp
    0.52
     LAMP
    0.52
    LAMP
    0.50
    Lamp
    0.46
    ランプ
    0.45
     lám
    0.45
     Lamps
    0.44
     lamps
    0.43
    Activations Density 0.000%

    No Known Activations