© 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. 112594
    Prev
    Next
    INDEX
    Explanations

    conspiracy to commit

    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
     This
    -1.96
     that
    -1.95
    Also
    -1.90
     Even
    -1.84
     Also
    -1.82
    僑
    -1.74
     schlechte
    -1.69
     We
    -1.67
     this
    -1.66
    Также
    -1.60
    POSITIVE LOGITS
    哢
    2.17
     a
    2.08
    注意事
    2.06
    sudadera
    1.91
    摃
    1.85
     juſ
    1.83
    Gratis
    1.80
     sè
    1.80
    textura
    1.80
    junge
    1.78
    Activations Density 0.044%

    No Known Activations