© 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. 210304
    Prev
    Next
    INDEX
    Explanations

    island or beach destination

    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
     제주
    0.84
    沖縄
    0.78
     tropical
    0.78
    Tropical
    0.78
    Hawaii
    0.77
     rainforest
    0.74
     Kauai
    0.74
    괌
    0.74
     Guam
    0.73
     Aloha
    0.73
    POSITIVE LOGITS
     Neigh
    0.45
     Killer
    0.43
     Anchor
    0.43
     Cancer
    0.41
     Dictionary
    0.40
     Unt
    0.39
     Tongue
    0.39
     Secret
    0.39
     anchor
    0.38
     Rabbit
    0.38
    Activations Density 0.009%

    No Known Activations