© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 76519
    Prev
    Next
    INDEX
    Explanations

    article a

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

    The neuron responds strongly to the indefinite article “a” when it appears as a separate token.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     also
    -1.51
    も
    -1.19
    を
    -1.14
    が
    -1.05
    と
    -1.02
     especially
    -1.02
    それも
    -1.00
     especialmente
    -0.99
    一样的
    -0.99
     weiteren
    -0.98
    POSITIVE LOGITS
    zaamheid
    1.30
     variety
    1.27
    }$,
    1.17
    明日は
    1.16
    為に
    1.09
     myriad
    1.09
    cili
    1.07
    
    1.03
    ビックリ
    1.03
    leh
    1.03
    Activations Density 0.255%

    No Known Activations