© 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. 78530
    Prev
    Next
    INDEX
    Explanations

    automated systems and processes

    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
    Mange
    -0.90
     intrepid
    -0.88
    ens
    -0.87
     melo
    -0.87
     sloven
    -0.80
     timid
    -0.79
    Comunic
    -0.78
     مخصوص
    -0.78
     mania
    -0.76
     nötig
    -0.76
    POSITIVE LOGITS
     teller
    1.21
     Teller
    1.16
     Automatic
    1.16
     автомати
    1.09
    ptonshire
    1.06
    teller
    1.04
    tellers
    1.02
     processes
    1.02
    Automatic
    1.00
    ﻖ
    0.98
    Activations Density 0.033%

    No Known Activations