© 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. 10-GEMMASCOPE-RES-131K
    7. 58688
    Prev
    Next
    INDEX
    Explanations

    every [noun]

    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_10/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
    ↵
    -3.38
     dando
    -2.91
     dritte
    -2.83
    ar
    -2.64
     fazendo
    -2.63
    ⟞
    -2.63
     delightfully
    -2.58
    
    -2.55
     THOSE
    -2.41
    ఽ
    -2.39
    POSITIVE LOGITS
    there
    3.55
     Even
    3.03
    Every
    3.00
    蕯
    2.89
    Although
    2.86
    Despite
    2.86
    Semua
    2.86
     There
    2.78
    Both
    2.78
    Even
    2.75
    Activations Density 0.042%

    No Known Activations