© 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. 10-GEMMASCOPE-RES-131K
    7. 69491
    Prev
    Next
    INDEX
    Explanations

    import stream or bytes

    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_10/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
     then
    -1.70
     إذا
    -1.64
     and
    -1.51
    4
    -1.48
     reason
    -1.48
     penso
    -1.42
     でも
    -1.40
     with
    -1.38
    1
    -1.33
     there
    -1.32
    POSITIVE LOGITS
    embroidered
    1.73
    。
    1.73
    chtenstein
    1.59
    fought
    1.57
     significado
    1.57
    knitted
    1.56
    ⑊
    1.56
    ,\\
    1.54
     constitue
    1.52
    likler
    1.52
    Activations Density 0.009%

    No Known Activations