© 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. 30164
    Prev
    Next
    INDEX
    Explanations

    multilingual linguistic structures

    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
     כי
    0.46
     כדי
    0.41
     を
    0.41
     لإ
    0.40
     poiché
    0.40
     anise
    0.40
     عشان
    0.39
     pasir
    0.39
     koska
    0.39
    bbene
    0.39
    POSITIVE LOGITS
     ataupun
    0.54
     deverá
    0.51
    టువంటి
    0.50
    х
    0.46
    着的
    0.46
     içerisinde
    0.44
    들도
    0.44
    ми
    0.44
    ,</
    0.43
     весьма
    0.43
    Activations Density 0.077%

    No Known Activations