© 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. 16-GEMMASCOPE-2-RES-262K
    7. 6228
    Prev
    Next
    INDEX
    Explanations

    Resident Evil

    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_16_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
     to
    0.59
     \
    0.58
    ing
    0.55
    ING
    0.51
     nhàng
    0.51
     has
    0.51
    ă
    0.50
     $\
    0.50
    f
    0.49
    z
    0.49
    POSITIVE LOGITS
    き
    0.54
    ३
    0.51
    他的
    0.50
    اي
    0.47
    }")
    0.47
    któ
    0.46
     состоянии
    0.45
    🆈
    0.45
     продолжает
    0.44
    ни
    0.44
    Activations Density 0.135%

    No Known Activations