© 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. 86322
    Prev
    Next
    INDEX
    Explanations

    now + realization/intention

    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
    ↵↵
    -2.44
    us
    -1.93
    {
    -1.84
    in
    -1.73
    ut
    -1.71
     
    -1.65
    ul
    -1.65
    man
    -1.52
     böyle
    -1.52
    ag
    -1.51
    POSITIVE LOGITS
    their
    2.13
    厹
    2.05
    嫆
    2.00
    傒
    1.95
     telefonu
    1.88
    𓆏
    1.86
     素描
    1.84
    懨
    1.81
     薬局
    1.80
    鲧
    1.80
    Activations Density 0.021%

    No Known Activations