© 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. 117594
    Prev
    Next
    INDEX
    Explanations

    equipment logs and records

    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
     calidad
    -0.84
     Rio
    -0.81
    Electricity
    -0.73
    很是
    -0.73
    Keb
    -0.72
     exporters
    -0.72
     manchen
    -0.72
     nuevos
    -0.71
     agricole
    -0.71
    ACTED
    -0.70
    POSITIVE LOGITS
     cannibal
    1.01
     discrepancies
    0.98
     conde
    0.89
     condemnation
    0.84
     items
    0.84
     discrepancy
    0.83
     condemning
    0.78
     particolar
    0.77
     Wives
    0.77
     item
    0.76
    Activations Density 0.016%

    No Known Activations