© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 27646
    Prev
    Next
    INDEX
    Explanations

    harbor, port, canal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Maui
    0.47
    车
    0.47
     ഏറ്റ
    0.46
     车
    0.46
     Schnee
    0.44
     Khao
    0.44
    鎂
    0.44
    🐆
    0.42
    氘
    0.42
    ôme
    0.42
    POSITIVE LOGITS
     harbor
    0.68
    canal
    0.67
     canal
    0.66
     dock
    0.63
     बंदर
    0.59
     Ports
    0.57
     port
    0.56
     harbour
    0.56
    Ports
    0.55
     kanal
    0.54
    Activations Density 0.065%

    No Known Activations