© 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. 9980
    Prev
    Next
    INDEX
    Explanations

    input or expect

    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
    を使った
    -1.53
    </h4>
    -1.52
    を用
    -1.51
    </h2>
    -1.49
    を搭載
    -1.47
    を使用した
    -1.47
     PUSTAKA
    -1.45
     семьи
    -1.40
    ↵↵↵↵↵↵↵
    -1.34
     schnee
    -1.34
    POSITIVE LOGITS
     What
    1.77
     This
    1.59
     When
    1.56
     Because
    1.49
     or
    1.40
     in
    1.38
     If
    1.38
    Törté
    1.35
     Have
    1.30
     if
    1.29
    Activations Density 0.004%

    No Known Activations