© 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. 41608
    Prev
    Next
    INDEX
    Explanations

    for {purpose, scope, duration}

    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
    いい
    -2.63
    見
    -2.47
    皤
    -2.36
     jabón
    -2.33
    ться
    -2.30
     bricolaje
    -2.28
    ܼ
    -2.28
     voilà
    -2.27
     vinilo
    -2.25
    𝑧
    -2.25
    POSITIVE LOGITS
     awhile
    2.98
     example
    2.92
    L
    2.89
    ges
    2.83
    </h3>
    2.66
    for
    2.63
    go
    2.61
    .“
    2.59
    0
    2.56
    as
    2.53
    Activations Density 0.668%

    No Known Activations