© 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. 22-GEMMASCOPE-RES-131K
    7. 11225
    Prev
    Next
    INDEX
    Explanations

    separate or within components

    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
    ayaquil
    -0.87
    enerbahçe
    -0.81
    chke
    -0.73
    ースト
    -0.72
    ürger
    -0.70
    一族
    -0.70
    Tb
    -0.69
    āci
    -0.69
     unfamiliar
    -0.68
    ovsky
    -0.68
    POSITIVE LOGITS
     separate
    1.40
     included
    1.34
    separate
    1.28
     separable
    1.27
     component
    1.26
     detachable
    1.21
    Separate
    1.18
     Separate
    1.17
     within
    1.16
     separately
    1.16
    Activations Density 0.295%

    No Known Activations