© 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. 106997
    Prev
    Next
    INDEX
    Explanations

    oe, ec, oes, oem

    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
     détaillés
    -0.77
     oblivious
    -0.73
     低
    -0.71
     perquè
    -0.70
     subjected
    -0.70
     ブル
    -0.69
     وب
    -0.69
    וני
    -0.69
    tives
    -0.69
     강
    -0.68
    POSITIVE LOGITS
    carrinho
    0.85
    Gü
    0.77
    ebp
    0.72
     Quite
    0.72
    equipo
    0.71
    polski
    0.71
     PBT
    0.70
    cjach
    0.70
    الو
    0.70
    Combat
    0.70
    Activations Density 0.033%

    No Known Activations