© 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. 33652
    Prev
    Next
    INDEX
    Explanations

    semester or term

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

    The neuron activates on mentions of the word “semester” (often when followed by a number).

    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
     distritos
    -1.97
    羕
    -1.95
     parís
    -1.88
     понял
    -1.82
     広場
    -1.79
     giusti
    -1.78
     soggior
    -1.78
     sám
    -1.77
    ceğim
    -1.77
     incontr
    -1.74
    POSITIVE LOGITS
    for
    2.06
    (
    2.03
    the
    2.00
    ↵↵
    1.85
                            
    1.80
    as
    1.80
    <bos>
    1.69
    I
    1.63
    .
    1.63
    isNullOrEmpty
    1.62
    Activations Density 0.005%

    No Known Activations