© 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. 34-GEMMASCOPE-RES-131K
    7. 58130
    Prev
    Next
    INDEX
    Explanations

    programming and technical terms

    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_34/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
    layın
    -0.90
     الحالة
    -0.88
     уже
    -0.84
    они
    -0.83
    kram
    -0.83
    XmlAttribute
    -0.82
     calculer
    -0.82
    RemoveAt
    -0.82
     çünkü
    -0.81
    keri
    -0.81
    POSITIVE LOGITS
     Silhouette
    0.89
     correctly
    0.82
    Tarea
    0.81
     memberships
    0.80
     другая
    0.80
    二维
    0.80
     specializing
    0.79
     needs
    0.78
    Dimen
    0.77
     sued
    0.77
    Activations Density 0.052%

    No Known Activations