© 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. 42131
    Prev
    Next
    INDEX
    Explanations

    things seem or appear

    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
     has
    -1.64
    {
    -1.42
    bracht
    -1.41
    )=
    -1.41
    anches
    -1.38
     «
    -1.38
    remacy
    -1.38
    vão
    -1.34
     seamlessly
    -1.34
     both
    -1.34
    POSITIVE LOGITS
     dekoratif
    1.82
    ㍉
    1.63
    差不多
    1.59
    〬
    1.57
    brakk
    1.53
    ㈯
    1.53
    richtet
    1.52
    The
    1.52
     tunik
    1.52
    selben
    1.49
    Activations Density 0.007%

    No Known Activations