© 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. 99248
    Prev
    Next
    INDEX
    Explanations

    we our

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

    The neuron activates on first-person plural pronouns (e.g. “we,” “our”) indicating a collective speaker or group reference.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     our
    -1.52
    HostException
    -1.45
    endpush
    -1.43
    FINED
    -1.39
    …"
    -1.38
     Mereka
    -1.32
     you
    -1.31
    Pgina
    -1.31
     wła
    -1.29
    vět
    -1.29
    POSITIVE LOGITS
     I
    1.39
    While
    1.30
     Ideally
    1.27
    々な
    1.25
     ३
    1.24
    an
    1.23
     derzeit
    1.23
     visst
    1.23
    Responding
    1.23
    大致
    1.23
    Activations Density 0.026%

    No Known Activations