© 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. 13867
    Prev
    Next
    INDEX
    Explanations

    payroll, ACH, checks, deposit, processing

    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
     intérprete
    -1.38
    .”
    -1.38
    ”.
    -1.16
    躄
    -1.15
     even
    -1.14
    ([
    -1.13
    rospy
    -1.13
    蛸
    -1.10
    不被
    -1.09
     Великобрита
    -1.08
    POSITIVE LOGITS
    ョン
    1.23
     Bourgoin
    1.14
    』『
    1.14
    散发
    1.13
    」、「
    1.12
    欧阳
    1.11
     buhay
    1.11
     mignon
    1.11
     Why
    1.10
     gezet
    1.08
    Activations Density 0.045%

    No Known Activations