© 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. 53034
    Prev
    Next
    INDEX
    Explanations

    delve deep into

    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
    RUPTION
    0.40
     edo
    0.37
    法
    0.36
    ים
    0.35
     خب
    0.34
    द
    0.34
    塑造
    0.34
    下面
    0.34
     estat
    0.33
     disampaikan
    0.33
    POSITIVE LOGITS
     этой
    0.54
     이러한
    0.52
     justement
    0.52
     этих
    0.51
    そんな
    0.48
     solchen
    0.48
     সেই
    0.46
     rash
    0.44
     такой
    0.44
     इन्हीं
    0.44
    Activations Density 0.047%

    No Known Activations