© 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. 12037
    Prev
    Next
    INDEX
    Explanations

    multiplication and calculation expressions

    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
     suddiv
    0.43
    㸮
    0.41
    ว่าเป็น
    0.40
    getNome
    0.40
    纣
    0.39
    usehen
    0.37
    lumat
    0.36
    രുവ
    0.36
    ước
    0.36
    té
    0.35
    POSITIVE LOGITS
     ×
    1.31
     multiplied
    1.30
    乘以
    1.21
     multiplying
    1.18
    ×
    1.10
     multiplies
    1.09
     multiply
    1.09
     multiplication
    1.09
     Multiply
    1.09
    multiply
    1.06
    Activations Density 0.055%

    No Known Activations