© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 10170
    Prev
    Next
    INDEX
    Explanations

    Sunni, glomer, Seng, nltk, ListBox

    np_acts-logits-general · gemini-2.5-flash-lite

    words containing the substring "glomer" (related to glomerular/kidney terminology) or proper nouns and terms containing "Seng"/"seng".

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
    t
    -3.23
    In
    -3.13
    C
    -2.95
    {
    -2.70
    L
    -2.67
    With
    -2.64
    m
    -2.61
    }
    -2.58
    k
    -2.58
    F
    -2.56
    POSITIVE LOGITS
    䜣
    3.78
    谖
    3.69
    geſ
    3.13
    
    3.11
    ፨
    2.92
    ቍ
    2.88
    ⸫
    2.83
    ⬈
    2.81
    ⮑
    2.80
    噲
    2.70
    Activations Density 0.025%

    No Known Activations