© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 91128
    Prev
    Next
    INDEX
    Explanations

    meeting diagnostic criteria

    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
    gye
    -0.88
     translateY
    -0.88
    ContextCompat
    -0.86
    OCOLATE
    -0.85
    temberg
    -0.82
    concep
    -0.82
     كور
    -0.79
    SetTitle
    -0.79
     tradic
    -0.77
     Cec
    -0.77
    POSITIVE LOGITS
     criteria
    6.59
    criteria
    4.78
     Criteria
    4.78
    Criteria
    4.69
     criterion
    4.63
     CRITERIA
    3.78
     criter
    3.75
     criterios
    3.56
    criterion
    3.55
     critères
    3.55
    Activations Density 0.184%

    No Known Activations