© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-16K
    4. 13769
    Prev
    Next
    INDEX
    Explanations

    mathematical calculations

    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_16k_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
    Lateral
    0.41
     никак
    0.39
    柽
    0.39
     lateral
    0.38
    橡胶
    0.38
    三角形
    0.38
     レザー
    0.38
     использовали
    0.37
    洳
    0.37
    摇
    0.37
    POSITIVE LOGITS
     Seventy
    0.45
     malls
    0.41
     Sixty
    0.40
    ponder
    0.40
    PLAC
    0.40
     seventy
    0.38
     Fifty
    0.38
     eighty
    0.38
     १८४
    0.38
     hana
    0.38
    Activations Density 0.152%

    No Known Activations