© 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. 78637
    Prev
    Next
    INDEX
    Explanations

    ranging between and across locations

    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
    مدیر
    -0.89
     a
    -0.84
     다른
    -0.78
     especially
    -0.78
     innych
    -0.78
     haup
    -0.77
     intermédiaire
    -0.77
     affitto
    -0.77
    致力
    -0.77
     insbesondere
    -0.75
    POSITIVE LOGITS
    czyna
    1.20
     tip
    1.15
     beyond
    1.05
     tận
    1.02
     Cape
    0.98
     fingertips
    0.97
    beyond
    0.96
     north
    0.94
     horizon
    0.92
     titik
    0.90
    Activations Density 0.044%

    No Known Activations