© 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. 52609
    Prev
    Next
    INDEX
    Explanations

    about or alternative

    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
    騰
    0.48
    什么是
    0.44
    टने
    0.43
     ominous
    0.42
     troubling
    0.42
     ಹೊಸ
    0.42
    뭡
    0.41
    productive
    0.41
     প্রাসাদ
    0.41
    なに
    0.41
    POSITIVE LOGITS
     or
    0.52
     أيضاً
    0.45
     یا
    0.42
    /
    0.41
     ወይም
    0.40
     বা
    0.40
     или
    0.40
     også
    0.39
     ankaŭ
    0.39
     single
    0.38
    Activations Density 0.014%

    No Known Activations