© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 4482
    Prev
    Next
    INDEX
    Explanations

    their

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

    The neuron is primarily triggered by tokens that express possession or ownership (e.g. possessive pronouns and related forms).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ému
    0.58
    ╾
    0.57
     quatrième
    0.57
    opération
    0.56
     három
    0.56
     méthod
    0.56
     második
    0.55
     troisième
    0.55
     girişim
    0.54
     deuxième
    0.54
    POSITIVE LOGITS
     minds
    0.69
     hearts
    0.68
     imagination
    0.62
     sensibilities
    0.60
    Z
    0.59
    J
    0.59
     Intents
    0.58
     味
    0.57
    N
    0.57
    R
    0.57
    Activations Density 0.017%

    No Known Activations