© 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. 10-GEMMASCOPE-RES-131K
    7. 42873
    Prev
    Next
    INDEX
    Explanations

    born

    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
    玬
    -1.54
    ```
    -1.50
    ↵↵
    -1.50
    缡
    -1.48
    $\
    -1.45
    亲爱的
    -1.40
    翾
    -1.40
    芨
    -1.39
    <tbody>
    -1.38
    <i>
    -1.37
    POSITIVE LOGITS
    ’
    2.13
    𐄙
    1.76
     numerosi
    1.69
     cielos
    1.66
    侂
    1.61
    abinieri
    1.59
    ㈮
    1.59
     boneka
    1.59
     dieci
    1.59
     neumáticos
    1.58
    Activations Density 0.011%

    No Known Activations