© 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-65K
    7. 27702
    Prev
    Next
    INDEX
    Explanations

    behavior, password, et cetera, employee

    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_65k_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
    現
    0.49
    平和
    0.46
    മ
    0.46
    Quality
    0.44
    Diversity
    0.44
    ကျ
    0.44
    如果是
    0.44
    溫度
    0.44
    此
    0.44
    به
    0.43
    POSITIVE LOGITS
     kucch
    0.58
     caroten
    0.54
     pique
    0.52
     bulging
    0.51
     Tutak
    0.50
     prone
    0.50
     croche
    0.50
     harem
    0.49
     cenderung
    0.48
    hami
    0.48
    Activations Density 0.052%

    No Known Activations