© 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. 17420
    Prev
    Next
    INDEX
    Explanations

    nuevo Leon

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

    Property Crime

    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
     сх
    0.42
    ките
    0.42
    antip
    0.40
     Dubey
    0.40
    intre
    0.39
    adona
    0.39
     سق
    0.38
     S
    0.38
    dds
    0.38
    dns
    0.37
    POSITIVE LOGITS
     LEON
    0.65
     Léon
    0.62
     Leon
    0.61
     leon
    0.59
    Leon
    0.56
    leon
    0.55
     leo
    0.53
     León
    0.50
    leo
    0.49
     लियो
    0.47
    Activations Density 0.000%

    No Known Activations