© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 103771
    Prev
    Next
    INDEX
    Explanations

    it followed by a verb

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

    This neuron activates on occurrences of the pronoun “it” (including “It,” “it,” and its contractions like “it’s” or “it is”).

    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
     batal
    -1.02
     iub
    -1.00
     will
    -0.99
     fabrica
    -0.97
    vincible
    -0.96
    rably
    -0.94
     declara
    -0.94
    任何人
    -0.94
    媲
    -0.94
     turco
    -0.93
    POSITIVE LOGITS
     all
    1.54
     isn
    1.33
     you
    1.20
     not
    1.16
     seems
    1.14
     oluyor
    1.08
     wasn
    1.06
     doesn
    1.06
     just
    1.02
     easy
    0.97
    Activations Density 0.037%

    No Known Activations