© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 45641
    Prev
    Next
    INDEX
    Explanations

    back up your system

    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
    လိုအပ်
    0.46
    ্রম
    0.44
    不得不
    0.42
    滹
    0.42
     factories
    0.41
     একটা
    0.41
    裡的
    0.41
    曺
    0.40
     борь
    0.40
    鍍
    0.39
    POSITIVE LOGITS
    ijima
    0.45
    ่าน
    0.44
    lent
    0.43
    id
    0.43
    numero
    0.41
     परिश
    0.41
    pyrazin
    0.41
    હાર
    0.41
     Kindern
    0.40
    auto
    0.40
    Activations Density 0.003%

    No Known Activations