© 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. 31442
    Prev
    Next
    INDEX
    Explanations

    job postings

    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
     kutoka
    -1.09
    kosten
    -0.95
     تحتوي
    -0.86
    名詞
    -0.85
    ={}
    -0.82
    tilha
    -0.81
     pintu
    -0.80
    ∐
    -0.79
    anada
    -0.79
     cuartos
    -0.79
    POSITIVE LOGITS
     applicants
    1.83
     position
    1.56
     salary
    1.52
     applicant
    1.46
     candidates
    1.39
     Applicants
    1.36
     positions
    1.34
    Salary
    1.30
     Must
    1.30
     preferably
    1.30
    Activations Density 0.095%

    No Known Activations