© 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. 34-GEMMASCOPE-RES-131K
    7. 77242
    Prev
    Next
    INDEX
    Explanations

    January 6th and related events

    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
    oluto
    -0.87
     Kawasaki
    -0.86
    čiai
    -0.79
    IIT
    -0.76
     Callahan
    -0.73
     instalação
    -0.72
    rags
    -0.71
    AMY
    -0.71
     efeitos
    -0.71
    êm
    -0.71
    POSITIVE LOGITS
     Jan
    2.39
     January
    2.25
     Capitol
    1.81
    Jan
    1.80
    January
    1.63
     insurrection
    1.63
     january
    1.60
    Capitol
    1.58
     jan
    1.38
     JAN
    1.34
    Activations Density 0.012%

    No Known Activations