© 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. 34-GEMMASCOPE-RES-131K
    7. 31636
    Prev
    Next
    INDEX
    Explanations

    set up

    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_34/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
    对你
    -0.93
    durch
    -0.88
    汇报
    -0.88
    時間も
    -0.87
    acces
    -0.82
     subjug
    -0.81
    diger
    -0.79
    Ст
    -0.79
    孭
    -0.79
     Eure
    -0.78
    POSITIVE LOGITS
     aside
    2.05
     up
    1.80
    aside
    1.36
     forth
    1.36
    Aside
    1.13
     sail
    1.09
     Aside
    1.05
    erus
    1.02
     apart
    1.02
     goals
    1.00
    Activations Density 0.020%

    No Known Activations