© 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. 10-GEMMASCOPE-RES-131K
    7. 43386
    Prev
    Next
    INDEX
    Explanations

    sum of two

    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
     Still
    -1.41
    就开始
    -1.38
    pecting
    -1.34
     wäre
    -1.32
     Could
    -1.27
     podían
    -1.23
    洒落
    -1.21
     help
    -1.21
     project
    -1.20
     tendremos
    -1.20
    POSITIVE LOGITS
     with
    1.87
     different
    1.82
     two
    1.65
     using
    1.52
     of
    1.48
    different
    1.46
    other
    1.45
     others
    1.45
     cdti
    1.41
    دیگر
    1.38
    Activations Density 0.120%

    No Known Activations