© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 4936
    Prev
    Next
    INDEX
    Explanations

    returns None or max

    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
    咅
    0.43
    鹭
    0.41
     ध्वनि
    0.41
    াক্ত
    0.40
    BleStatus
    0.40
    蛍光
    0.39
     পরিণত
    0.39
     thiệu
    0.38
    upakan
    0.38
    톄
    0.38
    POSITIVE LOGITS
     if
    0.52
    if
    0.43
     如果
    0.43
     If
    0.42
     মাসের
    0.42
     wat
    0.41
    If
    0.41
     Lor
    0.41
     chère
    0.40
     lor
    0.40
    Activations Density 0.021%

    No Known Activations