© 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. 33113
    Prev
    Next
    INDEX
    Explanations

    programming return

    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
    他也
    -0.95
     Successfully
    -0.92
     três
    -0.91
     أيضًا
    -0.90
     différentes
    -0.88
    actually
    -0.87
     tatsächlich
    -0.85
    でん
    -0.85
    क्स
    -0.85
     Quickly
    -0.84
    POSITIVE LOGITS
    🌸
    0.95
     ролях
    0.91
    рович
    0.86
    🐰
    0.85
    ńskich
    0.85
    miR
    0.85
     nuage
    0.83
    ❄️
    0.82
    😍
    0.81
    ☁
    0.81
    Activations Density 0.001%

    No Known Activations