© 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. 63802
    Prev
    Next
    INDEX
    Explanations

    advanced placement and honors courses

    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
     woollen
    -0.79
    Mathematics
    -0.75
    TIM
    -0.72
    ทาง
    -0.71
     Bengaluru
    -0.71
    ฿
    -0.70
     Cruelty
    -0.69
     Tym
    -0.68
    MATH
    -0.68
    エンジン
    -0.68
    POSITIVE LOGITS
     Honors
    1.44
     honors
    1.43
     AP
    1.32
     Advanced
    1.10
    Honors
    1.05
    AP
    1.03
    PAP
    1.02
     advanced
    1.01
     PAP
    0.98
     Adv
    0.92
    Activations Density 0.016%

    No Known Activations