© 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-262K
    7. 109530
    Prev
    Next
    INDEX
    Explanations

    concepts and descriptions

    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_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
    maß
    0.43
    inguished
    0.40
    𐰤
    0.39
     गरे
    0.39
     neka
    0.38
     mè
    0.38
     reconhecimento
    0.38
    muir
    0.38
    कांक्षा
    0.37
    䥑
    0.37
    POSITIVE LOGITS
    אה
    0.44
     покры
    0.38
     UAS
    0.37
     способен
    0.37
     shrou
    0.37
    在他的
    0.36
     Rest
    0.36
     ಟ
    0.36
    aea
    0.36
     ट्रॉप
    0.35
    Activations Density 0.000%

    No Known Activations