© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 68274
    Prev
    Next
    INDEX
    Explanations

    symbols and code snippets

    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_22/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
     before
    -1.33
     Lakukan
    -1.22
     on
    -1.15
     ducato
    -1.14
     stronę
    -1.13
     after
    -1.07
     treno
    -1.06
     Kebijakan
    -1.05
     Uniwers
    -1.03
     Manajemen
    -1.03
    POSITIVE LOGITS
    ちょこ
    1.12
    来週
    1.05
    の絵
    1.04
     czasem
    1.03
     verläng
    0.99
    Джере
    0.99
     Psi
    0.98
    glad
    0.98
     сообщает
    0.97
     rempli
    0.96
    Activations Density 0.079%

    No Known Activations