© 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. 5957
    Prev
    Next
    INDEX
    Explanations

    abstract concepts and modification

    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
    筠
    0.49
     vídeo
    0.48
    accident
    0.45
    罒
    0.45
    jim
    0.42
    έν
    0.42
    ome
    0.41
    ="+
    0.40
    tomorrow
    0.40
    didn
    0.40
    POSITIVE LOGITS
     configure
    0.52
     configured
    0.49
     chimiques
    0.49
     ઘ
    0.46
     obscures
    0.46
    ชี
    0.45
     caesar
    0.45
     เป็น
    0.44
     systematically
    0.44
     شیمی
    0.44
    Activations Density 0.001%

    No Known Activations