© 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. 22-GEMMASCOPE-RES-131K
    7. 72559
    Prev
    Next
    INDEX
    Explanations

    referring to specific people or things

    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_22/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
    еремо
    -1.08
     wohin
    -1.06
    LUS
    -0.94
     ILS
    -0.94
    פורט
    -0.94
    ӥ
    -0.93
     يقول
    -0.91
     этому
    -0.90
     rivet
    -0.88
     retraction
    -0.88
    POSITIVE LOGITS
     referring
    1.22
     their
    1.18
     specifically
    1.13
    Specifically
    1.07
     estrena
    1.02
     both
    1.01
     those
    0.98
    refer
    0.96
     dikeluarkan
    0.96
     current
    0.95
    Activations Density 0.022%

    No Known Activations