© 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. 65743
    Prev
    Next
    INDEX
    Explanations

    expresses an idea or thought

    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
     RECENT
    -1.29
    thx
    -1.22
    🐉
    -1.21
     exhortation
    -1.13
    ,
    -1.13
     slaugh
    -1.06
    without
    -1.06
    inent
    -1.05
    谆
    -1.04
    less
    -1.03
    POSITIVE LOGITS
     ideas
    1.58
     swój
    1.48
     first
    1.42
     Bélgica
    1.37
     ways
    1.33
     sebuah
    1.33
     could
    1.31
    亊
    1.30
     if
    1.30
     diferente
    1.30
    Activations Density 0.039%

    No Known Activations