© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 47948
    Prev
    Next
    INDEX
    Explanations

    numbers and time

    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
    鲧
    -1.69
     herbes
    -1.62
     rodriguez
    -1.60
     alebo
    -1.58
     lakini
    -1.55
    ミック
    -1.53
    usually
    -1.53
    probably
    -1.52
     \_
    -1.52
    wasn
    -1.51
    POSITIVE LOGITS
     any
    1.99
     some
    1.97
     from
    1.80
     an
    1.71
    </b>
    1.69
     all
    1.66
     about
    1.64
    </h5>
    1.63
     various
    1.60
     out
    1.59
    Activations Density 0.074%

    No Known Activations