© 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. 28080
    Prev
    Next
    INDEX
    Explanations

    alternative explanations

    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
     ชี
    0.49
     моря
    0.46
     produse
    0.44
     productos
    0.42
     금융
    0.42
     ጣ
    0.42
     prophecy
    0.41
    ，《
    0.41
     폭
    0.41
     محصولات
    0.41
    POSITIVE LOGITS
    kV
    0.46
    viz
    0.46
     સાથે
    0.45
    0
    0.45
    خة
    0.44
    ъз
    0.44
    堹
    0.44
    ساعدة
    0.44
    هاز
    0.43
    APH
    0.43
    Activations Density 0.011%

    No Known Activations