© 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. 15773
    Prev
    Next
    INDEX
    Explanations

    some, a few

    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
    あらゆる
    0.47
    各
    0.41
     segala
    0.39
     environments
    0.37
     each
    0.37
    哪个
    0.37
    ждый
    0.37
     audiences
    0.36
    那個
    0.36
    各个
    0.36
    POSITIVE LOGITS
     quelques
    1.55
     några
    1.48
     néhány
    1.38
     몇
    1.33
     câteva
    1.33
     einige
    1.30
     কিছু
    1.28
     birkaç
    1.28
     vài
    1.27
     Quelques
    1.27
    Activations Density 0.025%

    No Known Activations