© 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. 44559
    Prev
    Next
    INDEX
    Explanations

    location and posture summary

    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
    ↵
    -1.67
     
    -1.46
     for
    -1.46
    </b>
    -1.43
     will
    -1.42
    ）
    -1.41
    了些
    -1.41
    Those
    -1.39
     those
    -1.37
     which
    -1.35
    POSITIVE LOGITS
     FORMS
    1.63
     alip
    1.62
     fatale
    1.55
    ooooooo
    1.53
    ceased
    1.51
     taal
    1.49
     vocale
    1.47
     boya
    1.45
     adem
    1.44
     contente
    1.42
    Activations Density 0.013%

    No Known Activations