© 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. 2239
    Prev
    Next
    INDEX
    Explanations

    technical terms and definitions

    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
     and
    0.58
    และ
    0.57
     ਅਤੇ
    0.56
     மற்றும்
    0.53
    および
    0.52
     आणि
    0.51
     ۽
    0.51
     và
    0.50
     ಮತ್ತು
    0.50
    性和
    0.49
    POSITIVE LOGITS
     умолчанию
    0.39
     არს
    0.38
     unbelievable
    0.37
     unbelievably
    0.37
     चळ
    0.37
    ี่ยม
    0.37
    那一
    0.36
    듭
    0.36
     неизвест
    0.35
    빽
    0.35
    Activations Density 0.086%

    No Known Activations