© 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. 10-GEMMASCOPE-RES-131K
    7. 21034
    Prev
    Next
    INDEX
    Explanations

    academic programs and students

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

    The neuron responds to formal informational statements about academic programs or institutional offerings.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    ଶ
    -2.05
    ଷ
    -1.80
    ଵ
    -1.55
     manqué
    -1.39
     неприят
    -1.33
    ಆ
    -1.33
     Wartawan
    -1.30
    нс
    -1.30
    ױ
    -1.28
    Sziasztok
    -1.27
    POSITIVE LOGITS
     
    1.61
    nhung
    1.41
     учащихся
    1.40
     students
    1.38
     studies
    1.38
     územ
    1.36
    bàn
    1.35
    ·
    1.35
    onFailure
    1.34
    ÈNE
    1.34
    Activations Density 0.502%

    No Known Activations