© 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. 20358
    Prev
    Next
    INDEX
    Explanations

    numbers and calculations

    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
    0.46
     million
    0.45
     tomto
    0.44
    ০০০
    0.42
    -
    0.42
     thousand
    0.41
     milliards
    0.41
    १८६
    0.41
    ?????
    0.40
    iosity
    0.40
    POSITIVE LOGITS
    nętr
    0.43
    ">•
    0.42
     کمی
    0.42
    Мен
    0.40
    ется
    0.40
    स्की
    0.39
    气
    0.39
    ┙
    0.38
     ót
    0.37
     औषधि
    0.37
    Activations Density 0.138%

    No Known Activations