© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13756
    Prev
    Next
    INDEX
    Explanations

    specific details or measurements

    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
     tugas
    -1.58
     coisas
    -1.55
    usions
    -1.48
     belajar
    -1.46
     、
    -1.46
     même
    -1.46
    voer
    -1.44
    indicates
    -1.41
     Lösungen
    -1.40
    occurs
    -1.40
    POSITIVE LOGITS
     if
    1.63
     there
    1.37
     daarbij
    1.35
    渡し
    1.35
     offered
    1.34
     adequately
    1.33
     offering
    1.29
     provided
    1.28
     provide
    1.27
     també
    1.27
    Activations Density 0.301%

    No Known Activations