© 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. 22-GEMMASCOPE-RES-131K
    7. 27598
    Prev
    Next
    INDEX
    Explanations

    reporting speech

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

    The neuron strongly activates on first-person pronouns (especially “I”) and accompanying personal narrative statements.

    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
     dapatkan
    -1.14
     bahagia
    -1.08
    Tazama
    -1.06
     ferrovia
    -1.01
     verksamhet
    -1.00
     gustado
    -0.98
     wattpad
    -0.98
     algod
    -0.96
    IFYING
    -0.95
     copyrights
    -0.95
    POSITIVE LOGITS
     they
    1.52
     I
    1.34
     it
    1.21
     seem
    1.18
     but
    1.11
     mężczyzn
    1.08
     would
    1.04
     should
    1.04
     «
    1.03
    だと思います
    1.01
    Activations Density 0.010%

    No Known Activations