© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 74163
    Prev
    Next
    INDEX
    Explanations

    all plus abstract states

    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
    鶫
    -1.72
     devraient
    -1.68
    
    -1.65
    盉
    -1.61
     Lightboxes
    -1.58
     mismos
    -1.58
    縢
    -1.57
    臜
    -1.57
     devrait
    -1.55
     erhi
    -1.53
    POSITIVE LOGITS
     on
    2.13
     other
    1.86
     Following
    1.76
     In
    1.75
     To
    1.72
    </em>
    1.68
    ...
    1.61
     out
    1.57
     On
    1.56
    "
    1.55
    Activations Density 0.004%

    No Known Activations