© 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. 80794
    Prev
    Next
    INDEX
    Explanations

    PHP include or require statements

    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
     the
    -1.66
     tomadas
    -1.38
     diversité
    -1.34
     canadensis
    -1.34
     by
    -1.34
     bring
    -1.32
    utado
    -1.30
    ьем
    -1.30
     those
    -1.30
     brinde
    -1.30
    POSITIVE LOGITS
     egens
    1.48
    usually
    1.43
    either
    1.41
    often
    1.39
     другая
    1.34
    —,
    1.30
     cambiando
    1.30
    sometimes
    1.30
    fenced
    1.30
     extremely
    1.29
    Activations Density 0.030%

    No Known Activations