© 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. 40-GEMMASCOPE-2-RES-262K
    7. 101
    Prev
    Next
    INDEX
    Explanations

    math operations and equations

    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_40_width_262k_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
     courrier
    0.47
    凛
    0.47
     cynical
    0.45
    sponsor
    0.44
    資格
    0.43
    republik
    0.43
    忠
    0.42
     referrerpolicy
    0.42
    砥
    0.42
     MotoGP
    0.42
    POSITIVE LOGITS
     counting
    0.95
     Counting
    0.91
    Counting
    0.89
     subtraction
    0.88
    counting
    0.78
     multiplication
    0.77
     subtracting
    0.77
     Subtract
    0.77
     subtract
    0.75
     numerals
    0.74
    Activations Density 0.043%

    No Known Activations