© 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. 111602
    Prev
    Next
    INDEX
    Explanations

    social media videos

    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
    死了
    0.47
    死的
    0.47
     Spectacular
    0.45
    false
    0.43
    。
    0.42
    的最大
    0.42
    表面
    0.42
    ْنَ
    0.42
    istä
    0.41
     डेमो
    0.41
    POSITIVE LOGITS
    વ
    0.52
     envoyer
    0.48
     walang
    0.46
     bangun
    0.46
     sends
    0.45
     ouvido
    0.45
    untes
    0.44
     yere
    0.44
     ovat
    0.44
     отправ
    0.44
    Activations Density 0.002%

    No Known Activations