© 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. 58043
    Prev
    Next
    INDEX
    Explanations

    interior point method

    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
     minimization
    -0.94
     maximization
    -0.88
     sord
    -0.75
     Emmer
    -0.72
    アラ
    -0.71
     combinatorial
    -0.70
    ಾದ
    -0.69
     decision
    -0.69
    Gare
    -0.68
    Lunar
    -0.68
    POSITIVE LOGITS
     barrier
    1.03
    barrier
    0.94
     interior
    0.94
    Barrier
    0.93
     Barrier
    0.92
     Interior
    0.88
    centr
    0.85
    Interior
    0.84
    interior
    0.84
    peg
    0.80
    Activations Density 0.024%

    No Known Activations