© 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. 22-GEMMASCOPE-RES-131K
    7. 66244
    Prev
    Next
    INDEX
    Explanations

    function definitions or helper functions

    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
     kila
    -0.91
    šli
    -0.89
    ICULO
    -0.87
    cipais
    -0.86
    enciar
    -0.86
    IGOS
    -0.86
    五三
    -0.83
    となり
    -0.83
    ที่มา
    -0.81
    توضیحات
    -0.81
    POSITIVE LOGITS
     científicas
    1.05
     químicas
    0.94
     tekem
    0.93
    甄
    0.90
     ännu
    0.90
     snabbt
    0.90
    factura
    0.89
     dicen
    0.87
     behaupten
    0.87
    注意力
    0.87
    Activations Density 0.033%

    No Known Activations