© 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
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 6635
    Prev
    Next
    INDEX
    Explanations

    friends and friendship

    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_40_width_262k_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
    க்குற
    0.42
    გ
    0.40
    Sir
    0.39
    MOND
    0.38
    Outstanding
    0.38
    ானது
    0.38
    Ivo
    0.38
    Parent
    0.38
    M
    0.37
    AB
    0.37
    POSITIVE LOGITS
    👬
    0.86
    👭
    0.75
     เพื่อน
    0.69
     cercanos
    0.68
     whom
    0.67
     friendships
    0.66
     friends
    0.65
     acquaintances
    0.64
     prijatel
    0.63
     детства
    0.61
    Activations Density 0.020%

    No Known Activations