© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 12107
    Prev
    Next
    INDEX
    Explanations

    you may not use

    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_34/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
     can
    -2.34
     можно
    -1.49
     можна
    -1.43
     يمكن
    -1.42
    Can
    -1.20
     galima
    -1.19
     można
    -1.17
     Can
    -1.10
     CAN
    -1.10
     ويمكن
    -1.06
    POSITIVE LOGITS
     since
    0.86
    ihnachts
    0.86
     normally
    0.77
     поскольку
    0.76
    原本
    0.76
     ممکن
    0.76
    ='.$
    0.75
    lapsing
    0.75
    ]+
    0.74
     pulmon
    0.74
    Activations Density 0.014%

    No Known Activations