© 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-262K
    7. 57135
    Prev
    Next
    INDEX
    Explanations

    accumulating sums

    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_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
     वर्तमान
    0.40
     kehad
    0.40
     प्रकाशित
    0.39
    sé
    0.39
    these
    0.38
     Viewing
    0.38
    ।]
    0.37
     जिंद
    0.37
     ܐ
    0.36
     används
    0.36
    POSITIVE LOGITS
     summ
    0.44
    Gather
    0.43
    Accum
    0.42
     accumulator
    0.42
    总
    0.42
     accumulating
    0.41
    を集
    0.41
     summa
    0.40
     summation
    0.40
    =[];
    0.39
    Activations Density 0.143%

    No Known Activations