© 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. 41273
    Prev
    Next
    INDEX
    Explanations

    purpose or goal

    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
    offering
    -1.35
    depending
    -1.30
     essendo
    -1.29
    providing
    -1.29
    becoming
    -1.26
    estimable
    -1.24
    nante
    -1.22
    doing
    -1.22
    voir
    -1.21
     spannende
    -1.21
    POSITIVE LOGITS
     cuando
    1.87
     ultimately
    1.79
     When
    1.63
     finally
    1.62
     eventually
    1.61
     quando
    1.56
     when
    1.52
     better
    1.51
    1.45
     found
    1.38
    Activations Density 0.114%
    No Known Activations