© 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. 59671
    Prev
    Next
    INDEX
    Explanations

    long before, after, since, beyond

    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
    莛
    -2.09
    闞
    -2.03
     北市
    -2.00
    镲
    -1.98
     continually
    -1.94
    虯
    -1.91
    enablog
    -1.90
    戆
    -1.89
     praticamente
    -1.88
    鷙
    -1.88
    POSITIVE LOGITS
    li
    2.08
    It
    2.08
    f
    1.98
    "
    1.96
    !!!!
    1.96
    !!!!!
    1.87
    、
    1.86
    ll
    1.85
    ti
    1.84
    '
    1.84
    Activations Density 0.005%

    No Known Activations