© 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. 15006
    Prev
    Next
    INDEX
    Explanations

    demonstrative this/these

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron detects first-person statements lamenting how (increasingly) “busy” the speaker is.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    ⅗
    -1.04
    ärsk
    -1.02
     Schriftsteller
    -0.99
    ⅖
    -0.98
    cible
    -0.97
    }}+
    -0.97
     אם
    -0.96
     zespół
    -0.95
     unang
    -0.95
     FIVE
    -0.94
    POSITIVE LOGITS
     these
    2.28
     this
    2.27
     are
    1.41
     would
    1.26
     those
    1.20
     such
    1.20
     should
    1.16
     This
    1.16
     این
    1.13
     এই
    1.13
    Activations Density 0.106%

    No Known Activations