© 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. 52559
    Prev
    Next
    INDEX
    Explanations

    super prefix intensifier

    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
    و
    1.00
    т
    0.96
    ल
    0.93
    ل
    0.93
    一
    0.93
    א
    0.93
     powied
    0.92
    מ
    0.88
    س
    0.86
    ت
    0.85
    POSITIVE LOGITS
     super
    1.06
    SUPER
    0.93
    超級
    0.92
     সুপার
    0.91
    超级
    0.91
    ’
    0.91
    annuation
    0.85
    .
    0.83
     सुपर
    0.82
     Super
    0.80
    Activations Density 0.054%

    No Known Activations