© 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. 12825
    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
     and
    -2.00
    mutter
    -1.65
    lampe
    -1.63
     histó
    -1.58
     páns
    -1.55
    kredit
    -1.54
     dámské
    -1.54
    plastik
    -1.51
    ieR
    -1.51
    ори
    -1.51
    POSITIVE LOGITS
    k
    2.03
    c
    2.02
    x
    1.99
    z
    1.97
    r
    1.97
    _
    1.97
    f
    1.96
    l
    1.86
    m
    1.85
    u
    1.84
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.