© 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. 128906
    Prev
    Next
    INDEX
    Explanations

    setting titles and captions

    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
     seguido
    -1.43
     kejadian
    -1.34
     those
    -1.31
    齟
    -1.29
     such
    -1.29
     tradisi
    -1.29
    苦笑
    -1.27
    r
    -1.27
     kepercayaan
    -1.27
     famosa
    -1.23
    POSITIVE LOGITS
    橚
    1.80
     comté
    1.62
    ementara
    1.60
    اسم
    1.60
    tizia
    1.49
     estadounid
    1.48
    何か
    1.45
    這
    1.45
    鹟
    1.44
     时尚
    1.43
    Activations Density 0.010%

    No Known Activations