© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 72414
    Prev
    Next
    INDEX
    Explanations

    for each item or category

    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
    튿
    -1.70
    {
    -1.69
     parachoque
    -1.62
    𐍆
    -1.60
     factores
    -1.60
     usamos
    -1.58
     navegando
    -1.57
     plomo
    -1.55
    嘥
    -1.55
     installiert
    -1.55
    POSITIVE LOGITS
    ;
    2.17
     of
    2.09
     purposes
    2.06
     you
    2.06
     Then
    1.91
     /
    1.89
     this
    1.88
    r
    1.85
    L
    1.83
     då
    1.80
    Activations Density 0.011%

    No Known Activations