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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 70101
    Prev
    Next
    INDEX
    Explanations

    venture capital or firm

    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
    甞
    -3.22
    鬭
    -2.98
    鑁
    -2.97
    
    -2.92
    鱨
    -2.83
    癰
    -2.81
    柺
    -2.78
     pression
    -2.67
    猻
    -2.67
    Ⲉ
    -2.66
    POSITIVE LOGITS
     "
    3.41
     zahlreiche
    3.22
    </em>
    2.95
     verschied
    2.75
     These
    2.63
    ↵
    2.63
     einige
    2.58
     hallowed
    2.58
    但他
    2.58
    ’
    2.55
    Activations Density 0.003%

    No Known Activations