© 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. 2351
    Prev
    Next
    INDEX
    Explanations

    mathematical relationships and operations involving expressions and variables.

    oai_token-act-pair · gpt-4o-miniTriggered by @gersonkroiz

    calculating mathematical values

    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
    飏
    0.46
    财政
    0.45
    陆续
    0.43
    投资
    0.43
    浑
    0.43
    业协会
    0.43
    供应链
    0.43
    𒊬
    0.43
    ังหวัด
    0.42
    zących
    0.42
    POSITIVE LOGITS
    0.63
     the
    0.56
     =
    0.53
     $
    0.53
    2
    0.53
    0
    0.52
     \
    0.50
    if
    0.49
    frac
    0.49
     C
    0.49
    Activations Density 0.416%

    No Known Activations