© 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. 35998
    Prev
    Next
    INDEX
    Explanations

    multilingual words and math variables

    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
    た
    0.49
    知らせ
    0.42
     কমি
    0.41
     gunmen
    0.39
    ।)
    0.39
     conferencing
    0.39
     відо
    0.39
    鳧
    0.38
    வரின்
    0.38
     conformance
    0.38
    POSITIVE LOGITS
    ze
    0.50
     montaña
    0.46
     dzieci
    0.46
     आक
    0.46
     werkt
    0.46
    ग्राह
    0.45
    kont
    0.44
     Stalingrad
    0.44
     vectores
    0.43
    icu
    0.43
    Activations Density 0.001%

    No Known Activations