© 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. 11191
    Prev
    Next
    INDEX
    Explanations

    tag names

    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
     but
    -2.13
    挚
    -1.95
    睺
    -1.90
    鰨
    -1.84
     ناخن
    -1.80
    Привет
    -1.79
    ivotopis
    -1.76
     feroit
    -1.75
    ?'
    -1.74
    遄
    -1.74
    POSITIVE LOGITS
    geſ
    2.50
     único
    2.11
    
    2.06
     Verkä
    2.05
    ?
    2.03
     celebrations
    2.02
    O
    2.02
    ЭС
    1.95
     jako
    1.95
    målet
    1.95
    Activations Density 0.022%

    No Known Activations