© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108747
    Prev
    Next
    INDEX
    Explanations

    certification bodies and standards

    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
     prescription
    -1.08
     Prescription
    -0.84
     prescriptions
    -0.78
    Prescription
    -0.75
     Escribe
    -0.72
     Nerve
    -0.71
     descent
    -0.71
     prescri
    -0.70
     Rezept
    -0.69
    睫毛
    -0.69
    POSITIVE LOGITS
    tocin
    0.79
     julk
    0.79
    ่า
    0.79
    isée
    0.77
     Broncos
    0.75
    ENTINA
    0.75
    ensical
    0.74
    bdb
    0.74
    indt
    0.74
    transaction
    0.74
    Activations Density 0.006%

    No Known Activations