© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 73000
    Prev
    Next
    INDEX
    Explanations

    question and answer starters

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

    The neuron specifically fires on the preposition “by.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    Wiz
    -1.02
    ktör
    -0.94
     »
    -0.93
    しら
    -0.93
    骑士
    -0.92
    ஓ
    -0.91
    »»
    -0.91
     цель
    -0.90
    獷
    -0.90
     campaigns
    -0.89
    POSITIVE LOGITS
    vait
    1.14
    four
    1.13
     are
    1.08
    Xoxo
    1.05
     selected
    1.03
     tych
    1.03
    ὺς
    1.02
    emporio
    1.00
    力气
    0.99
    bearers
    0.99
    Activations Density 0.000%

    No Known Activations