© 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. 84686
    Prev
    Next
    INDEX
    Explanations

    by [name or code element]

    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
     relâche
    -1.36
    랏
    -1.35
     remonter
    -1.35
     possibilités
    -1.30
     cœurs
    -1.30
     attendre
    -1.26
     agujero
    -1.26
    üße
    -1.26
     acheté
    -1.25
     göm
    -1.25
    POSITIVE LOGITS
     you
    1.72
     after
    1.72
     These
    1.71
     When
    1.61
     when
    1.60
     before
    1.59
     during
    1.47
     cuando
    1.43
     How
    1.38
     without
    1.36
    Activations Density 0.023%

    No Known Activations