© 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. 53-GEMMASCOPE-2-RES-262K
    7. 19766
    Prev
    Next
    INDEX
    Explanations

    strange and related words

    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_53_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
    }{|\
    0.43
     மேற்க
    0.39
     mussels
    0.39
     kife
    0.38
    한강
    0.38
    )){
    0.38
    Deployed
    0.38
    闊
    0.38
     மி
    0.38
     रौ
    0.37
    POSITIVE LOGITS
     strange
    0.72
     Strange
    0.70
    Strange
    0.68
     стран
    0.65
    strange
    0.63
    奇怪
    0.56
     étr
    0.55
     estran
    0.51
     Strang
    0.51
     Calm
    0.50
    Activations Density 0.001%

    No Known Activations