© 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. 40-GEMMASCOPE-2-RES-65K
    7. 788
    Prev
    Next
    INDEX
    Explanations

    see myself out

    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_40_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
    ()=>{
    0.45
    ade
    0.41
    elten
    0.41
     Commencez
    0.41
     anál
    0.40
    orce
    0.40
     می‌کند
    0.40
    erves
    0.39
    afd
    0.39
    ort
    0.38
    POSITIVE LOGITS
     👀
    0.57
     below
    0.49
     clearly
    0.49
    能不能
    0.47
    👀
    0.47
    see
    0.47
     jelas
    0.45
     see
    0.44
     tuber
    0.43
    See
    0.42
    Activations Density 0.074%

    No Known Activations