© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 100341
    Prev
    Next
    INDEX
    Explanations

    http ://

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

    personal names and greetings in informal online communication like blog comments and forum posts.

    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
     ditawarkan
    -1.56
     katk
    -1.49
     concluyó
    -1.41
     potranno
    -1.41
     kemudian
    -1.40
     desmotiv
    -1.34
     türkiye
    -1.34
     that
    -1.33
    
    -1.31
     verranno
    -1.30
    POSITIVE LOGITS
     did
    1.43
     الشاشة
    1.30
     was
    1.29
    MORE
    1.24
    初め
    1.22
    ."
    1.20
     हम
    1.19
    ਸ
    1.19
    始め
    1.18
     antes
    1.17
    Activations Density 0.016%

    No Known Activations