© 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. 22-GEMMASCOPE-RES-131K
    7. 95687
    Prev
    Next
    INDEX
    Explanations

    . Good

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

    The neuron is highly sensitive to the first‐person plural possessive “our.”

    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
     millioner
    -1.01
    そこから
    -0.87
     That
    -0.86
    меся
    -0.84
    Here
    -0.84
    ⩩
    -0.83
     män
    -0.82
    That
    -0.82
     fallow
    -0.82
    들
    -0.81
    POSITIVE LOGITS
    itigen
    1.11
    lijker
    1.00
     RETURNS
    0.98
     pozdě
    0.97
     appris
    0.96
     này
    0.95
     otten
    0.95
     obje
    0.95
     本
    0.94
     später
    0.94
    Activations Density 0.018%

    No Known Activations