© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 380
    Prev
    Next
    INDEX
    Explanations

    my programming

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

    The neuron strongly activates on possessive pronouns (e.g. “my,” “our,” “their,” “its”)—i.e. words marking ownership or perspective.

    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
     
    0.27
     the
    0.25
     =
    0.25
    <0x0D>
    0.24
     -
    0.23
    }
    0.23
     a
    0.23
     [
    0.23
    0
    0.22
    =
    0.22
    POSITIVE LOGITS
     own
    0.25
     newfound
    0.25
     demeanor
    0.25
     burgeoning
    0.24
     penchant
    0.23
    ត្រូវការ
    0.22
     própria
    0.22
    కున్న
    0.22
     eigenes
    0.22
    ទទួលបាន
    0.22
    Activations Density 1.540%

    No Known Activations