© 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-65K
    7. 20678
    Prev
    Next
    INDEX
    Explanations

    dual, addition, walkways

    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_65k_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
    вка
    0.45
    мии
    0.43
    Pub
    0.43
     sagen
    0.43
    АТО
    0.42
    ٹن
    0.42
    카
    0.41
    jabi
    0.41
     chale
    0.41
    ﮩ
    0.41
    POSITIVE LOGITS
     Многие
    0.44
     yǔ
    0.44
     Ajoutez
    0.42
     walkways
    0.42
     საჭ
    0.41
     നിങ്ങളുടെ
    0.39
     kiddos
    0.39
    ➊
    0.39
     さらに
    0.39
    addition
    0.38
    Activations Density 0.006%

    No Known Activations