© 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. 34823
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns followed by nouns

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

    The neuron selectively detects possessive pronouns (e.g. “his,” “her,” “my,” “your”) in the text.

    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
    ˂
    -1.73
     kän
    -1.60
    urns
    -1.50
     correctes
    -1.49
    ˃
    -1.48
    jours
    -1.48
    ∅
    -1.45
    Ѕ
    -1.45
    ≅
    -1.40
     Chá
    -1.38
    POSITIVE LOGITS
    brtc
    1.58
    oczes
    1.51
     while
    1.41
    Ꮞ
    1.39
    خخ
    1.35
     deoarece
    1.34
    aneity
    1.30
     (!__
    1.30
     when
    1.29
     nedenle
    1.29
    Activations Density 0.122%

    No Known Activations