© 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. 42624
    Prev
    Next
    INDEX
    Explanations

    not followed by condition

    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
     same
    -2.06
    {
    -1.98
     the
    -1.94
    なども
    -1.82
    </h5>
    -1.76
    并没有
    -1.73
    re
    -1.73
    f
    -1.71
    archiwizowane
    -1.66
    their
    -1.64
    POSITIVE LOGITS
     réaliste
    2.02
    Croix
    1.83
    américa
    1.75
    大多
    1.74
    𝗚
    1.73
    的
    1.70
     compréhen
    1.62
    ко
    1.62
    стероид
    1.62
    нию
    1.61
    Activations Density 0.008%

    No Known Activations