© 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. 15679
    Prev
    Next
    INDEX
    Explanations

    as [adjective] as

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

    The neuron is keyed to the comparative “as” in simile or “as if” constructions.

    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
    ের
    1.15
    '
    1.15
    ים
    1.07
     angrily
    1.05
    kopf
    1.05
    tempo
    1.02
    kali
    1.02
    kimi
    1.02
    es
    1.01
     edificio
    1.00
    POSITIVE LOGITS
    inine
    1.16
    いない
    1.00
    sembles
    0.99
    ut
    0.94
     Tâm
    0.91
    િ
    0.89
    cribable
    0.88
    씐
    0.82
    ymmet
    0.81
    𝑅
    0.81
    Activations Density 0.037%

    No Known Activations