© 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. 10-GEMMASCOPE-RES-131K
    7. 129894
    Prev
    Next
    INDEX
    Explanations

    sensing technologies and principles

    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_10/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
    -2.08
     {
    -2.00
    Considering
    -1.98
    As
    -1.98
     и
    -1.92
     और
    -1.86
    二人の
    -1.82
    ついでに
    -1.81
    Having
    -1.76
    To
    -1.75
    POSITIVE LOGITS
     hectare
    2.05
     ſont
    2.00
     GOtt
    1.88
     spearheaded
    1.85
     Reſ
    1.84
    🫅
    1.84
    ρό
    1.80
     …..
    1.79
     himſelf
    1.78
     marte
    1.77
    Activations Density 0.007%

    No Known Activations