© 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. 9822
    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
     who
    -1.19
    ("")]
    -1.02
     easier
    -1.02
    satunya
    -0.97
     জন্য
    -0.94
     actually
    -0.92
    adine
    -0.91
     enjoys
    -0.90
     belongs
    -0.89
    起来了
    -0.88
    POSITIVE LOGITS
    СЯ
    0.98
    igerung
    0.97
    嶇
    0.92
    Planes
    0.92
     valg
    0.91
     rivales
    0.91
     bæ
    0.91
    поро
    0.91
    ือก
    0.91
     chy
    0.91
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.