© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 97765
    Prev
    Next
    INDEX
    Explanations

    of the, interesting explanation

    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
     several
    -1.00
     what
    -0.96
     had
    -0.90
     any
    -0.88
     those
    -0.88
     weren
    -0.86
    コロナ禍
    -0.86
    してしまった
    -0.85
     generates
    -0.85
     since
    -0.85
    POSITIVE LOGITS
     exceptionally
    0.97
     AMAZING
    0.95
     boreal
    0.88
     alcune
    0.86
     wonderfully
    0.84
     horrid
    0.84
     intriguing
    0.84
     delightfully
    0.83
     $*$
    0.82
     жк
    0.81
    Activations Density 0.001%

    No Known Activations