© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 48986
    Prev
    Next
    INDEX
    Explanations

    comes down to

    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_34/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
     comes
    -1.81
     come
    -1.72
     COMES
    -1.62
     Comes
    -1.56
    Comes
    -1.52
    Come
    -1.50
    comes
    -1.48
     Come
    -1.42
    come
    -1.32
    来
    -1.32
    POSITIVE LOGITS
     down
    2.73
    down
    1.55
    Down
    1.16
     back
    1.12
     to
    1.03
     reduced
    0.98
     Down
    0.92
     DOWN
    0.91
     Reduce
    0.82
     reduce
    0.80
    Activations Density 0.013%

    No Known Activations