© 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. 128550
    Prev
    Next
    INDEX
    Explanations

    month, day, and time stamps

    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
     that
    -1.21
     years
    -0.91
     населения
    -0.90
    を送
    -0.85
    らなかった
    -0.84
    “…”
    -0.83
    ="";
    -0.82
    摸了
    -0.82
    するという
    -0.82
     of
    -0.81
    POSITIVE LOGITS
    heds
    1.04
     originalen
    0.94
    ceous
    0.88
     invasión
    0.87
     kā
    0.87
    larak
    0.86
     produrre
    0.86
     porción
    0.85
    私が
    0.85
    8
    0.83
    Activations Density 0.001%

    No Known Activations