© 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. 14384
    Prev
    Next
    INDEX
    Explanations

    possessive pronoun body part

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

    The main thing this neuron does is detect possessive pronouns (like his, her, their, your) often in contexts referring to body parts or personal attributes.

    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
    Obrázky
    -1.27
    ⩾
    -1.16
    ⩽
    -1.12
     elke
    -1.12
     laat
    -1.05
     gostar
    -1.05
     value
    -1.04
    ≅
    -1.04
     sırt
    -1.03
    抿
    -1.03
    POSITIVE LOGITS
     both
    1.41
    vaila
    1.27
     Both
    1.20
    licante
    1.19
    Both
    1.19
    eronau
    1.18
     semacam
    1.16
    nachron
    1.16
    rugu
    1.15
     Recently
    1.14
    Activations Density 0.073%

    No Known Activations