© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 722
    Prev
    Next
    INDEX
    Explanations

    since followed by a past reference

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     
    -1.75
    9
    -1.74
    0
    -1.71
     others
    -1.44
    2
    -1.41
     then
    -1.35
    なども
    -1.34
    ↵↵↵↵↵↵↵↵↵↵↵↵↵
    -1.33
    も見
    -1.32
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -1.31
    POSITIVE LOGITS
     dala
    1.81
    𒊹
    1.69
    鏨
    1.66
     hro
    1.63
    
    1.60
     特写
    1.58
    絅
    1.55
     ministra
    1.53
    osob
    1.53
     vín
    1.52
    Activations Density 0.023%

    No Known Activations