© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 68001
    Prev
    Next
    INDEX
    Explanations

    Lord hath

    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
    </strong>
    -2.06
    菹
    -1.83
     klasa
    -1.76
     твои
    -1.70
    zwei
    -1.70
    findet
    -1.67
    ܖ
    -1.66
     timmar
    -1.65
     druga
    -1.64
    
    -1.63
    POSITIVE LOGITS
    </td>
    1.81
    men
    1.69
    <i>
    1.63
     as
    1.56
    чи
    1.41
     {
    1.40
     a
    1.35
    %;
    1.35
    de
    1.34
    ini
    1.34
    Activations Density 0.018%

    No Known Activations