© 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. 108525
    Prev
    Next
    INDEX
    Explanations

    code snippets 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_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
     this
    -0.98
    ≍
    -0.90
    しましたが
    -0.89
     ended
    -0.86
    応募
    -0.85
     did
    -0.84
     five
    -0.84
     found
    -0.83
     life
    -0.81
     menu
    -0.81
    POSITIVE LOGITS
    <code>
    1.15
    ä
    0.91
    Facilit
    0.91
    Figur
    0.88
    ඍ
    0.86
    IKA
    0.85
    ala
    0.84
     romances
    0.84
    kits
    0.84
     iii
    0.84
    Activations Density 0.000%

    No Known Activations