© 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. 27716
    Prev
    Next
    INDEX
    Explanations

    Australian context

    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
     ξεκ
    0.46
     behö
    0.44
     começar
    0.43
    趔
    0.42
    ตอนนี้
    0.41
    蜗
    0.41
     benefitted
    0.40
     Adap
    0.39
     setData
    0.39
     isn
    0.39
    POSITIVE LOGITS
    v
    0.53
    b
    0.50
    d
    0.47
    ic
    0.47
    y
    0.46
    s
    0.45
    k
    0.45
    f
    0.44
    j
    0.44
    破壊
    0.42
    Activations Density 0.001%

    No Known Activations