Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 29-GEMMASCOPE-2-RES-65K
    4. 708
    Prev
    Next
    INDEX
    Explanations

    arithmetic operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_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
    }}:=\
    0.60
    __))
    0.59
     splurge
    0.58
    તમ
    0.57
     vooral
    0.57
     sobretudo
    0.54
    zeichnung
    0.51
     rámci
    0.50
     국가
    0.50
    landish
    0.50
    POSITIVE LOGITS
     ×
    1.53
    ×
    1.47
    x
    1.32
     multiplied
    1.31
     x
    1.26
    乘以
    1.21
    𝑥
    1.20
     times
    1.10
     ÷
    1.05
     умно
    1.04
    Activations Density 1.093%

    No Known Activations