© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 109753
    Prev
    Next
    INDEX
    Explanations

    hexadecimal representations

    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_34/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
     what
    -1.38
     into
    -1.23
     should
    -1.19
     instead
    -1.10
     it
    -1.06
    鈈
    -1.05
    mbH
    -1.05
    さんです
    -1.02
    anskje
    -1.01
    了一会儿
    -1.01
    POSITIVE LOGITS
     bacté
    1.00
    很多人
    0.99
     éclairage
    0.98
    either
    0.95
     kapture
    0.95
     parcs
    0.95
     suivants
    0.94
     derniers
    0.94
     PvE
    0.94
    Ό
    0.93
    Activations Density 0.006%

    No Known Activations