© 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. 73752
    Prev
    Next
    INDEX
    Explanations

    possessive or reflexive pronouns

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

    The neuron principally fires on verbs denoting actions (including both gerund “-ing” forms and finite past-tense forms).

    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
     two
    -1.97
     only
    -1.75
     even
    -1.71
     just
    -1.59
     three
    -1.54
     always
    -1.53
     was
    -1.42
    If
    -1.41
     also
    -1.38
    Two
    -1.38
    POSITIVE LOGITS
     themselves
    3.59
    各自
    2.28
     their
    2.16
    themselves
    2.14
     birbir
    1.88
    各有
    1.77
     THEIR
    1.74
     leurs
    1.67
     έχουν
    1.67
     nhau
    1.60
    Activations Density 0.402%

    No Known Activations