© 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. 42819
    Prev
    Next
    INDEX
    Explanations

    mathematical sequences or equations

    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
     or
    -1.82
     our
    -1.75
     this
    -1.69
    }$_
    -1.55
     today
    -1.53
     cinturón
    -1.53
     cordón
    -1.51
    Dữ
    -1.49
     ganzes
    -1.48
     pintadas
    -1.47
    POSITIVE LOGITS
     eccl
    1.51
    .
    1.49
    有时候
    1.41
    作为
    1.40
     conve
    1.34
     Remembering
    1.29
     religieux
    1.27
    \
    1.26
     philosop
    1.23
     Usability
    1.23
    Activations Density 0.007%

    No Known Activations