© 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. 34-GEMMASCOPE-RES-131K
    7. 63430
    Prev
    Next
    INDEX
    Explanations

    on social media

    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
    áu
    -1.02
     liitty
    -0.98
     kuulu
    -0.98
     considérons
    -0.98
    NewUrlParser
    -0.96
    ͝
    -0.96
    estination
    -0.91
     eikä
    -0.90
     stanowi
    -0.89
     طبق
    -0.89
    POSITIVE LOGITS
     on
    4.94
     online
    3.89
     trên
    2.31
     via
    2.23
    online
    2.22
     онлайн
    2.03
    บน
    1.92
    Online
    1.91
     Online
    1.88
     ONLINE
    1.74
    Activations Density 0.119%

    No Known Activations