© 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. 130736
    Prev
    Next
    INDEX
    Explanations

    secondary or supplementary

    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_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
     fingerprint
    -0.84
     fourni
    -0.76
    त्त
    -0.74
    粼
    -0.74
    viro
    -0.74
    了一遍
    -0.73
    Lame
    -0.73
    ongono
    -0.73
    需要注意
    -0.73
     πο
    -0.71
    POSITIVE LOGITS
     secondary
    1.29
     additional
    1.06
     split
    1.02
     auxiliary
    0.98
    Split
    0.98
     another
    0.97
     supplementary
    0.97
    Secondary
    0.96
     supplemental
    0.94
     splitting
    0.93
    Activations Density 0.182%

    No Known Activations