© 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. 92918
    Prev
    Next
    INDEX
    Explanations

    student activities

    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
     dichas
    -0.79
     hacer
    -0.79
     solemn
    -0.76
    rui
    -0.75
     Rural
    -0.75
    ляр
    -0.73
    内存
    -0.71
    krivning
    -0.71
     võ
    -0.71
     Comb
    -0.71
    POSITIVE LOGITS
     student
    1.11
    Student
    0.96
     Student
    0.91
     Crimson
    0.89
    student
    0.84
     studen
    0.84
    学生
    0.82
     Daily
    0.81
     STUDENT
    0.81
     students
    0.79
    Activations Density 0.030%

    No Known Activations