© 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. 29125
    Prev
    Next
    INDEX
    Explanations

    numerical fractions and dates

    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
     There
    -2.86
    there
    -2.63
    {
    -2.56
    </strong>
    -2.53
    0
    -2.53
     from
    -2.48
    </b>
    -2.22
     slight
    -2.11
    There
    -2.09
     restrictions
    -2.08
    POSITIVE LOGITS
    溷
    2.39
    扛
    2.25
     certains
    2.19
    泚
    2.14
    脔
    2.08
     帅气
    2.05
     faciliter
    2.05
     siè
    2.03
    zaSy
    2.02
    笮
    2.02
    Activations Density 0.028%

    No Known Activations