© 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. 36337
    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
     cortar
    -1.02
     esponja
    -1.00
     our
    -0.99
    ایش
    -0.99
    ǧ
    -0.97
    سول
    -0.96
    Ễ
    -0.96
    震災
    -0.95
     Sén
    -0.94
     wciąż
    -0.93
    POSITIVE LOGITS
     and
    1.17
    achable
    1.03
    8
    1.01
    au
    0.93
    疑惑
    0.91
     وزار
    0.91
    olyb
    0.91
     (!__
    0.91
    stddef
    0.90
    âce
    0.89
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.