© 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. 103162
    Prev
    Next
    INDEX
    Explanations

    pickled vegetables, limes, herring

    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
     There
    -3.00
    {
    -2.94
    al
    -2.83
     It
    -2.64
    </strong>
    -2.36
     Also
    -2.36
    er
    -2.27
     Furthermore
    -2.20
     Clearly
    -2.19
     With
    -2.14
    POSITIVE LOGITS
    臜
    3.31
    ⑊
    2.11
     abond
    2.08
    责任编辑
    2.02
    蹀
    1.98
    ᠁
    1.95
    脔
    1.89
    érieurs
    1.88
    こともあります
    1.88
    鸶
    1.88
    Activations Density 0.002%

    No Known Activations