© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 71271
    Prev
    Next
    INDEX
    Explanations

    Rajmund, Monoclonal, Acute, BEAUTY

    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
     resolute
    -1.84
     fierce
    -1.84
     Also
    -1.82
     Additionally
    -1.80
     disgraceful
    -1.79
    荩
    -1.79
     Также
    -1.78
     Despite
    -1.77
     horrific
    -1.74
     Similarly
    -1.72
    POSITIVE LOGITS
     is
    2.08
    崀
    1.77
     pomocí
    1.75
    —
    1.70
    Ἢ
    1.70
    なんで
    1.64
    我们的
    1.60
     the
    1.60
    讓
    1.56
    或者
    1.53
    Activations Density 0.000%

    No Known Activations