© 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. 44601
    Prev
    Next
    INDEX
    Explanations

    railway station

    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
    ta
    -1.70
    </h3>
    -1.59
     сист
    -1.55
     renfer
    -1.55
     chré
    -1.53
    ⤻
    -1.52
    uſe
    -1.52
    します
    -1.46
    وس
    -1.46
    或者
    -1.45
    POSITIVE LOGITS
     to
    1.91
     будущего
    1.52
    こういう
    1.43
    ㅢ
    1.42
    風に
    1.42
    ↵↵
    1.38
    schedulers
    1.38
    自己是
    1.37
     blurred
    1.36
    美しく
    1.36
    Activations Density 0.013%

    No Known Activations