© 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. 48867
    Prev
    Next
    INDEX
    Explanations

    emerged, arrived, necessary

    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
    скіх
    0.53
     giocando
    0.47
    Donc
    0.46
     гром
    0.45
    멧
    0.45
     giochi
    0.45
     gioco
    0.44
    绿
    0.44
     rubric
    0.43
     reimag
    0.42
    POSITIVE LOGITS
    必要な
    0.54
     customers
    0.52
     khách
    0.50
    ፈላጊ
    0.50
     තම
    0.48
     आपले
    0.47
     passengers
    0.46
     सुरक्षित
    0.46
    nThe
    0.46
     सफलतापूर्वक
    0.45
    Activations Density 0.003%

    No Known Activations