© 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. 108393
    Prev
    Next
    INDEX
    Explanations

    ingredients for garnishing

    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
     BEHIND
    -0.98
     verhind
    -0.94
    みそ
    -0.91
    是怎么回事
    -0.91
    リンゴ
    -0.90
     atyp
    -0.90
    กล้
    -0.90
     lentils
    -0.89
    contained
    -0.89
     eggplant
    -0.88
    POSITIVE LOGITS
     additional
    1.55
     sprinkle
    1.30
     chopped
    1.23
     sprinkled
    1.20
     some
    1.20
     garnish
    1.15
     crushed
    1.09
     scattered
    1.09
     tiny
    1.07
    cr
    1.05
    Activations Density 0.016%

    No Known Activations