© 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-262K
    7. 101084
    Prev
    Next
    INDEX
    Explanations

    search product, citizenship, jewelry

    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_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
    ופ
    0.48
    стре
    0.47
    डाउन
    0.46
    اده
    0.45
    Notation
    0.44
    шен
    0.44
    క్‌
    0.44
    ጨ
    0.44
    ቒ
    0.44
    ਦ
    0.42
    POSITIVE LOGITS
    珠宝
    0.46
     selfishness
    0.46
     jewelry
    0.46
     triggers
    0.45
     blindness
    0.45
     elementi
    0.44
     softness
    0.42
    erry
    0.41
     blankets
    0.41
     Jewelry
    0.41
    Activations Density 0.000%

    No Known Activations