© 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. 28405
    Prev
    Next
    INDEX
    Explanations

    lights on and indicating

    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
     pueden
    -1.33
     mogą
    -1.31
    因此
    -1.22
    ごち
    -1.20
     sehingga
    -1.20
     to
    -1.20
     можем
    -1.20
    HasBeenSet
    -1.19
     Therefore
    -1.19
    zędu
    -1.17
    POSITIVE LOGITS
     on
    1.67
     indicating
    1.48
     indicate
    1.34
     denoting
    1.32
    ñado
    1.22
    toHaveBeen
    1.20
     quartos
    1.20
     esmal
    1.20
     indicates
    1.18
    ⚕
    1.18
    Activations Density 0.028%

    No Known Activations