© 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. 22-GEMMASCOPE-RES-131K
    7. 72828
    Prev
    Next
    INDEX
    Explanations

    established updated showed distribution

    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
    ayashi
    -1.05
     poteva
    -0.98
    קות
    -0.91
    хать
    -0.90
    vikle
    -0.84
    ީ
    -0.83
     construit
    -0.80
    fieras
    -0.79
     aforementioned
    -0.79
    condido
    -0.79
    POSITIVE LOGITS
     corresponding
    0.93
     eftersom
    0.87
    なのだ
    0.82
    ранее
    0.82
     correspondingly
    0.82
    cześ
    0.81
    levant
    0.80
    Similarly
    0.78
    moder
    0.77
     luon
    0.77
    Activations Density 0.093%

    No Known Activations