© 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. 67838
    Prev
    Next
    INDEX
    Explanations

    Guanqiao

    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
     kaos
    -2.09
     bunda
    -2.09
     was
    -1.95
    她
    -1.91
    是
    -1.86
     caricatura
    -1.82
    。】
    -1.80
    。　
    -1.79
    UNDA
    -1.79
     seksi
    -1.72
    POSITIVE LOGITS
     which
    1.80
     you
    1.66
    くださった
    1.61
    玙
    1.59
    大切
    1.53
    だら
    1.51
     cuyos
    1.43
    大切に
    1.41
    方で
    1.41
    和你
    1.38
    Activations Density 0.005%

    No Known Activations