© 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. 73742
    Prev
    Next
    INDEX
    Explanations

    political campaign committee

    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
     for
    -1.70
     communs
    -1.55
     if
    -1.53
     essentiels
    -1.50
     normaux
    -1.49
    -
    -1.43
     can
    -1.41
     positifs
    -1.38
     škol
    -1.36
     autén
    -1.31
    POSITIVE LOGITS
    ↵↵
    2.34
     zusätzliche
    1.63
     genaue
    1.61
    ⢪
    1.58
     französische
    1.55
     unangemessene
    1.54
     persönliche
    1.54
    あぁ
    1.52
     öffentliche
    1.50
    mortem
    1.49
    Activations Density 0.002%

    No Known Activations