© 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. 11969
    Prev
    Next
    INDEX
    Explanations

    hyphens or dashes

    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
    ya
    -1.59
    余談
    -1.42
    ついでに
    -1.36
    //
    -1.34
     h
    -1.32
    end
    -1.28
     использовать
    -1.27
    为例
    -1.25
    こんな感じで
    -1.24
     =
    -1.23
    POSITIVE LOGITS
     logros
    1.77
     asamblea
    1.70
    矬
    1.68
    umesc
    1.67
     veckor
    1.66
    igers
    1.66
     ingreso
    1.59
    erequisite
    1.57
    astian
    1.56
     encuesta
    1.54
    Activations Density 0.023%

    No Known Activations