© 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. 66564
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Sadly
    -0.98
    titura
    -0.95
    Thankfully
    -0.93
    Somebody
    -0.91
    cibility
    -0.89
    源码
    -0.88
    Recently
    -0.86
     сковоро
    -0.86
    洀
    -0.85
    beforeAll
    -0.84
    POSITIVE LOGITS
    =/
    1.15
    тент
    1.09
     and
    1.09
     atau
    1.08
    ].(
    0.95
    quared
    0.94
    ᵀ
    0.94
     hetzelfde
    0.93
     Penis
    0.93
     &&
    0.90
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.