© 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. 22-GEMMASCOPE-RES-131K
    7. 12915
    Prev
    Next
    INDEX
    Explanations

    levels and stages

    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_22/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
     slightly
    -1.13
     slight
    -0.98
     remain
    -0.89
     remained
    -0.83
     when
    -0.82
     additional
    -0.82
     half
    -0.81
     focusing
    -0.81
     on
    -0.80
     medical
    -0.78
    POSITIVE LOGITS
    最後
    0.94
     противополо
    0.89
    Jam
    0.88
    far
    0.87
     遠
    0.86
     samenwerking
    0.85
     infine
    0.85
     geliefert
    0.84
    遠く
    0.82
    すっかり
    0.82
    Activations Density 0.059%

    No Known Activations