© 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. 47724
    Prev
    Next
    INDEX
    Explanations

    license language

    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
     ChatGPT
    -1.11
     NFTs
    -1.09
     Türkiye
    -1.01
     metaverse
    -0.97
     Wordle
    -0.91
     Stell
    -0.88
     NFT
    -0.87
     Inflation
    -0.85
     omicron
    -0.81
    Stell
    -0.80
    POSITIVE LOGITS
     coronavirus
    1.13
    Coronavirus
    0.84
     Coronavirus
    0.84
    coronavirus
    0.83
     corona
    0.82
    SafeMath
    0.82
     quarantined
    0.74
    melon
    0.73
     drastic
    0.73
    corona
    0.72
    Activations Density 0.004%

    No Known Activations