© 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. 31-GEMMASCOPE-2-RES-16K
    7. 257
    Prev
    Next
    INDEX
    Explanations

    have/has followed by been

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

    The neuron is detecting occurrences of the verb “have” (especially its past form “had”).

    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_31_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
    -
    0.32
     ,
    0.30
     =
    0.30
    }
    0.29
     |
    0.29
     -
    0.29
    ">
    0.29
    .-
    0.29
    <unused63>
    0.29
    =
    0.29
    POSITIVE LOGITS
     been
    0.64
     fått
    0.60
     gotten
    0.52
     BEEN
    0.52
     ollut
    0.50
    been
    0.50
     undergone
    0.49
     begun
    0.48
    Been
    0.48
     vært
    0.48
    Activations Density 0.809%

    No Known Activations