© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 27780
    Prev
    Next
    INDEX
    Explanations

    name, Q, Welcome, Twitter

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

    This neuron detects Django migration field-option tokens and their values (e.g. on_delete, delete, null, blank, SET, True, ContentType).

    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
    LEBR
    -1.18
     its
    -1.13
    iertes
    -1.05
     lel
    -1.04
     reú
    -1.04
     hini
    -1.03
     kön
    -1.02
    〜。
    -1.00
     persil
    -0.99
     Spanyol
    -0.98
    POSITIVE LOGITS
    </i>
    1.05
    urts
    1.02
    isse
    0.98
     Secre
    0.97
     also
    0.92
    ga
    0.90
     b
    0.90
     after
    0.90
     '</
    0.90
     mu
    0.89
    Activations Density 0.001%

    No Known Activations