© 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. 5426
    Prev
    Next
    INDEX
    Explanations

    give + pronouns/up/birth

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

    The neuron strongly activates on the verb “give,” i.e. it detects occurrences of “give” in the text.

    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
    RI
    1.05
    lining
    1.02
    RA
    1.00
    ROLL
    0.98
    FISH
    0.96
    EE
    0.94
    RIGHT
    0.93
    g
    0.88
    ów
    0.84
    te
    0.84
    POSITIVE LOGITS
     generously
    1.16
    ductory
    1.04
     geeft
    1.02
    یہ
    0.99
    rocyte
    0.97
     verand
    0.95
     termasuk
    0.94
     kepada
    0.93
     Gives
    0.93
    ्यारह
    0.93
    Activations Density 0.001%

    No Known Activations