© 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. 116560
    Prev
    Next
    INDEX
    Explanations

    it is / Es ist

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

    The neuron fires on impersonal third-person subject pronouns (e.g. “it,” “Es,” “Il”) at the start of a clause.

    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
     веке
    -1.09
    
    -1.02
    atiques
    -1.00
    quelize
    -0.98
    rebbe
    -0.98
     restoran
    -0.96
     materiais
    -0.96
    ēt
    -0.95
     januar
    -0.95
    barung
    -0.95
    POSITIVE LOGITS
     is
    1.35
     was
    1.27
     there
    1.22
    俩
    1.17
    ]
    1.09
     happens
    1.08
     easier
    1.04
     faut
    1.04
     suffices
    0.99
     tratta
    0.97
    Activations Density 0.002%

    No Known Activations