© 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. 10812
    Prev
    Next
    INDEX
    Explanations

    "$schema" keys

    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
     that
    -0.99
    tarif
    -0.85
    plantas
    -0.85
    IBILITY
    -0.84
    atação
    -0.83
    thentic
    -0.82
    wishlist
    -0.81
    抉
    -0.81
     История
    -0.80
    setConfig
    -0.79
    POSITIVE LOGITS
    a
    0.89
    apart
    0.86
    也在
    0.85
    thorax
    0.83
     añade
    0.82
    把我
    0.82
    бол
    0.81
    .}
    0.81
     nerede
    0.81
     Erlangen
    0.81
    Activations Density 0.051%

    No Known Activations