© 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. 9807
    Prev
    Next
    INDEX
    Explanations

    multi-language nouns

    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
    1
    -3.25
    /
    -2.52
    9
    -2.36
    :
    -2.36
    8
    -2.33
    0
    -2.27
    4
    -2.22
    *
    -2.17
    6
    -2.17
    ?
    -2.08
    POSITIVE LOGITS
    ↵
    2.25
    を始め
    2.17
     núcleos
    2.05
    狨
    1.99
     haupts
    1.97
     harika
    1.93
     vendedores
    1.92
     monumentos
    1.92
     numerosas
    1.84
    谵
    1.84
    Activations Density 0.004%

    No Known Activations