© 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. 13797
    Prev
    Next
    INDEX
    Explanations

    different planets and skies

    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
    _
    0.42
    については
    0.42
    وح
    0.39
     validity
    0.38
     प्रश्नों
    0.38
    éma
    0.37
    オブ
    0.37
    ཚ
    0.37
    ഫ്
    0.37
     Analysis
    0.36
    POSITIVE LOGITS
     vecchio
    0.48
     depois
    0.45
     incroyable
    0.44
    вки
    0.43
     viejo
    0.43
     vieja
    0.43
     Leute
    0.42
    బ్బు
    0.42
     nuevos
    0.41
    👾
    0.41
    Activations Density 0.021%

    No Known Activations