© 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. 22-GEMMASCOPE-RES-131K
    7. 14884
    Prev
    Next
    INDEX
    Explanations

    numbers and technical terms

    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_22/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
     naive
    -0.89
    veti
    -0.88
    pondre
    -0.88
     modifies
    -0.86
     they
    -0.86
     ignores
    -0.85
     that
    -0.85
     restricts
    -0.84
    otheby
    -0.83
    ISLAM
    -0.82
    POSITIVE LOGITS
     позволяют
    0.92
    лением
    0.86
     komfort
    0.82
    🫃
    0.82
     Belgien
    0.81
    וּ
    0.81
     MOUNTAIN
    0.79
    Costs
    0.79
    Cost
    0.77
     acquist
    0.77
    Activations Density 0.088%

    No Known Activations