© 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. 93340
    Prev
    Next
    INDEX
    Explanations

    api endpoints and classes

    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
    camiseta
    -1.23
    Inne
    -1.22
     elástico
    -1.17
    tarta
    -1.16
    scarpe
    -1.16
    ________,
    -1.15
     elevador
    -1.15
     jurídico
    -1.15
    我们是
    -1.13
     esponja
    -1.13
    POSITIVE LOGITS
    5
    1.45
    4
    1.40
    6
    1.36
    at
    1.30
    has
    1.29
    is
    1.29
    3
    1.27
    8
    1.27
    ๊ก
    1.27
    to
    1.23
    Activations Density 0.006%

    No Known Activations