© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 804
    Prev
    Next
    INDEX
    Explanations

    as an AI / a large language model

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

    The neuron strongly activates on occurrences of the word “as” (including capitalized “As”) used to introduce a clause.

    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
    tage
    0.73
    ERE
    0.66
    List
    0.65
    Field
    0.63
    ENO
    0.62
    ()
    0.60
    the
    0.60
    s
    0.59
    Table
    0.59
    Hamburg
    0.58
    POSITIVE LOGITS
    bestos
    0.92
    inine
    0.84
    sembles
    0.83
    ymptotic
    0.82
    ynchron
    0.82
    ymmetrical
    0.80
    sembling
    0.77
    sembled
    0.75
    olutely
    0.74
    ymmetric
    0.71
    Activations Density 0.052%

    No Known Activations